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. 19-RESID-POST-AA
    6. 24650
    Prev
    Next
    INDEX
    Explanations

    say ending in ":"

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omedical
    -0.07
     trí
    -0.07
    طلع
    -0.07
     comb
    -0.07
    奇
    -0.06
    fried
    -0.06
    诊断
    -0.06
    geometry
    -0.06
    知道自己
    -0.06
    ект
    -0.06
    POSITIVE LOGITS
     inquiries
    0.07
    省教育厅
    0.07
    dana
    0.07
    项目经理
    0.07
    查获
    0.07
     Pow
    0.07
    𝐎
    0.07
     обор
    0.07
    霰
    0.07
    (answer
    0.07
    Activations Density 0.003%

    No Known Activations