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

    Neuronpedia

    APICircuit 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. 7004
    Prev
    Next
    INDEX
    Explanations

    code and number sequences

    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
    リング
    -0.07
     StringUtil
    -0.07
    .prom
    -0.07
     trimming
    -0.07
    单调
    -0.07
    مصطفى
    -0.06
    .Utility
    -0.06
    websocket
    -0.06
    员工
    -0.06
    .bundle
    -0.06
    POSITIVE LOGITS
    𝜋
    0.07
    中文
    0.07
     Picks
    0.07
    ("__
    0.07
     topping
    0.07
    insk
    0.07
     Attack
    0.07
    /x
    0.07
     Blade
    0.07
    屏幕
    0.06
    Activations Density 0.043%

    No Known Activations