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. 130993
    Prev
    Next
    INDEX
    Explanations

    male

    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
     준
    -0.07
     explore
    -0.07
     vampires
    -0.07
    -score
    -0.06
     Vulkan
    -0.06
    如今
    -0.06
    ewn
    -0.06
    .has
    -0.06
     Numerous
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    抓捕
    0.08
    信息发布
    0.08
    ープ
    0.07
     Industry
    0.07
    福田
    0.07
    打赢
    0.07
    gift
    0.07
    htdocs
    0.07
    (inputStream
    0.07
    中关
    0.07
    Activations Density 0.005%

    No Known Activations