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. 44014
    Prev
    Next
    INDEX
    Explanations

    period

    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
    terdam
    -0.08
    見える
    -0.07
    JM
    -0.07
    (entries
    -0.07
    再生能源
    -0.06
    החלט
    -0.06
     stm
    -0.06
    /me
    -0.06
    ㉥
    -0.06
    是什么呢
    -0.06
    POSITIVE LOGITS
    (bot
    0.07
     CPPUNIT
    0.07
     wipe
    0.07
     respects
    0.07
    颉
    0.07
     Supplies
    0.07
    	line
    0.07
    _None
    0.07
     Dispatcher
    0.06
    _PRESENT
    0.06
    Activations Density 0.092%

    No Known Activations