Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 87878
    Prev
    Next
    INDEX
    Explanations

    say "want"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Washer
    -0.07
    .getBoolean
    -0.07
    etime
    -0.07
    amaged
    -0.07
    㑇
    -0.07
    瞪
    -0.07
    -Agent
    -0.07
    .ms
    -0.06
    Ḻ
    -0.06
    棕色
    -0.06
    POSITIVE LOGITS
    :${
    0.07
    Blockchain
    0.07
    splice
    0.07
     ***/↵
    0.07
     ביק
    0.07
    AH
    0.07
    UU
    0.07
    phe
    0.07
    _);↵↵
    0.07
    SCR
    0.07
    Activations Density 0.001%

    No Known Activations