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. 27-RESID-POST-AA
    6. 131070
    Prev
    Next
    INDEX
    Explanations

    Business acquisitions

    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_27/trainer_1
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ancestry
    -0.07
    .full
    -0.07
     الكبر
    -0.07
    .extend
    -0.07
    tuple
    -0.06
    运转
    -0.06
     [-
    -0.06
    ﯻ
    -0.06
    杜绝
    -0.06
    .decode
    -0.06
    POSITIVE LOGITS
    _dem
    0.07
    婧
    0.07
    appointment
    0.07
    ekt
    0.07
    鸟类
    0.07
    IDO
    0.07
    ushi
    0.07
     Sel
    0.06
     báo
    0.06
     kel
    0.06
    Activations Density 0.001%

    No Known Activations