© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 83770
    Prev
    Next
    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash

    Tokens that mark speaker/role or conversation boundaries (special control tokens like system/user/assistant and turn delimiters).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    年第
    -0.08
     opcion
    -0.07
    インター�
    -0.07
     зарегистрирова
    -0.07
    .locals
    -0.07
     trackers
    -0.07
    Ώ
    -0.07
    nodeName
    -0.07
     k
    -0.07
     culo
    -0.07
    POSITIVE LOGITS
    formats
    0.07
     FirebaseAuth
    0.07
    RETURN
    0.07
    atabases
    0.07
    山脉
    0.06
    undles
    0.06
    诈
    0.06
    이라는
    0.06
    ///↵
    0.06
    cano
    0.06
    Activations Density 0.174%

    No Known Activations