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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 11-TRANSCODER-HP
    4. 46426
    Prev
    Next
    INDEX
    Explanations

    weather

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_11.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.11.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģĵãģ¨ãģ§ãģĻ
    -0.29
    å·¥åķĨ
    -0.28
     recip
    -0.26
    ä¹ħ
    -0.25
    cott
    -0.25
     Gut
    -0.24
    ç¼Ħ
    -0.24
    езÑĥлÑĮÑĤ
    -0.24
    çīĻ
    -0.23
     fif
    -0.23
    POSITIVE LOGITS
    ason
    0.30
    als
    0.26
    çļĦéľĢæ±Ĥ
    0.26
    rowsable
    0.26
     sequel
    0.25
    çļĦæĢĿæĥ³
    0.25
    (SQL
    0.25
    ASON
    0.24
    /features
    0.24
     Semantic
    0.24
    Activations Density 0.055%

    No Known Activations