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. 131067
    Prev
    Next
    INDEX
    Explanations

    Re

    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
     Privacy
    -0.07
    兴奋
    -0.07
    .='
    -0.06
    حرية
    -0.06
     DK
    -0.06
     AFC
    -0.06
     ha
    -0.06
    存在着
    -0.06
     referring
    -0.06
    (range
    -0.06
    POSITIVE LOGITS
     Preis
    0.08
    太极
    0.07
    쯔
    0.07
    引用日期
    0.07
     tứ
    0.07
    _BLE
    0.07
    手机号
    0.07
    še
    0.07
     exceeded
    0.06
    Quantity
    0.06
    Activations Density 0.002%

    No Known Activations