© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7522
    Prev
    Next
    INDEX
    Explanations

    locks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CAPITAL
    -0.30
    累计
    -0.29
    ãģĹãģ¦ãģĦãģı
    -0.28
    累积
    -0.25
    #End
    -0.25
    igans
    -0.25
     cumulative
    -0.23
     nắm
    -0.23
     Cum
    -0.23
    ç»Ī身
    -0.23
    POSITIVE LOGITS
     cof
    0.27
     Eu
    0.26
    èĵ¬
    0.26
     ios
    0.26
    ä¼łåĩº
    0.26
     geomet
    0.25
    é£İ
    0.25
     program
    0.25
    .browser
    0.25
     proved
    0.24
    Activations Density 0.009%

    No Known Activations