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. 131065
    Prev
    Next
    INDEX
    Explanations

    Pharmaceutical/chemical context

    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
    abol
    -0.07
     transformer
    -0.07
     Mono
    -0.07
    BOOLE
    -0.06
    .degree
    -0.06
    蛆
    -0.06
    Nor
    -0.06
    _tar
    -0.06
     nature
    -0.06
     professionals
    -0.06
    POSITIVE LOGITS
    	My
    0.08
    狁
    0.07
    澼
    0.07
    בוט
    0.07
     mừng
    0.07
    evenodd
    0.07
    耨
    0.07
     yabancı
    0.06
     cellForRowAt
    0.06
     frenzy
    0.06
    Activations Density 0.003%

    No Known Activations