© 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 EvalsExportsAPI 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. 76776
    Prev
    Next
    INDEX
    Explanations

    Webpage/code snippets

    np_max-act · gemini-2.0-flash

    the ends of user messages / conversation turn boundaries (the end-of-turn token, especially for user turns).

    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
    жен
    -0.07
    uestion
    -0.07
    ｪ
    -0.06
     fileType
    -0.06
    ”.↵↵
    -0.06
     ['-
    -0.06
    ɳ
    -0.06
    �
    -0.06
    ););↵
    -0.06
     Institutions
    -0.06
    POSITIVE LOGITS
    秘诀
    0.07
    巅峰
    0.07
    IELDS
    0.06
    (Guid
    0.06
    _HEADER
    0.06
     Separ
    0.06
    娶
    0.06
    PARAM
    0.06
     LY
    0.06
    咒
    0.06
    Activations Density 0.115%

    No Known Activations