Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 24591
    Prev
    Next
    INDEX
    Explanations

    say "Simple" or "String"

    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
    进化
    -0.07
    _();↵
    -0.06
    깁
    -0.06
    杀菌
    -0.06
    接连
    -0.06
    HttpGet
    -0.06
     Aynı
    -0.06
    塑胶
    -0.06
    (OpCodes
    -0.06
     caric
    -0.06
    POSITIVE LOGITS
     AABB
    0.07
    auto
    0.07
    ไหว
    0.07
    力争
    0.07
    '
    0.06
    latex
    0.06
     worth
    0.06
    Moon
    0.06
    speaker
    0.06
    owego
    0.06
    Activations Density 0.001%

    No Known Activations