© 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. 7389
    Prev
    Next
    INDEX
    Explanations

    General English text

    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
    HW
    -0.26
    ç®ĢåİĨ
    -0.25
    çľĭä¸įåĩº
    -0.25
     hy
    -0.24
     undisclosed
    -0.24
    Charlotte
    -0.24
    -LAST
    -0.23
     unle
    -0.23
    ä¼Ĭæĭī
    -0.23
    umb
    -0.23
    POSITIVE LOGITS
    ooke
    0.28
    дан
    0.28
    allest
    0.26
    æĸ°æ¨¡å¼ı
    0.26
    /*@
    0.24
    -radius
    0.24
    kas
    0.24
    çļĭ
    0.24
    ordial
    0.24
    .rate
    0.24
    Activations Density 0.004%

    No Known Activations