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. 131028
    Prev
    Next
    INDEX
    Explanations

    German language

    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
     TODAY
    -0.08
    任何形式
    -0.07
     nhuận
    -0.07
    较快
    -0.07
     OBS
    -0.07
     الرئيسية
    -0.07
    🏦
    -0.07
     קבוע
    -0.07
    _NORMAL
    -0.07
     ALIGN
    -0.07
    POSITIVE LOGITS
     Resistance
    0.08
    옜
    0.08
     citizens
    0.07
    再也没有
    0.06
     sıc
    0.06
     Township
    0.06
     Marble
    0.06
    mage
    0.06
    ゐ
    0.06
    Resistance
    0.06
    Activations Density 0.013%

    No Known Activations