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. 131047
    Prev
    Next
    INDEX
    Explanations

    Game files and directories

    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
     suffer
    -0.08
     roaring
    -0.08
    常州
    -0.08
     Smoking
    -0.07
    kręc
    -0.07
     swearing
    -0.07
    も多い
    -0.07
    pare
    -0.07
     Burning
    -0.07
    疬
    -0.07
    POSITIVE LOGITS
    eday
    0.08
    ellidos
    0.07
    /embed
    0.07
     petite
    0.07
    >;↵
    0.07
    談
    0.07
    개발
    0.06
    입
    0.06
    /year
    0.06
    מדד
    0.06
    Activations Density 0.062%

    No Known Activations