© 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. 84079
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    tokens that are part of markup/code structure (HTML/XML tags, attributes, and other code/formatting tokens).

    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
    ARRANT
    -0.07
     Evidence
    -0.07
    เถ
    -0.06
    تجديد
    -0.06
    /url
    -0.06
     prol
    -0.06
     cigaret
    -0.06
    送达
    -0.06
    燠
    -0.06
    (Session
    -0.06
    POSITIVE LOGITS
    1
    0.14
     of
    0.12
    ↵
    0.12
    ↵↵
    0.11
    .↵
    0.11
    ↵
    0.10
    .↵↵
    0.09
    的
    0.09
    。↵
    0.08
     in
    0.08
    Activations Density 9.142%

    No Known Activations