© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 8283
    Prev
    Next
    INDEX
    Explanations

    coronavirus

    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
    elson
    -0.30
    æĸĩ
    -0.29
    éģ¥
    -0.27
    jal
    -0.27
     wrongful
    -0.26
    uptools
    -0.25
    ValuePair
    -0.25
    è¿ľç¨ĭ
    -0.25
     interrupts
    -0.24
    éĽĨä¸Ń
    -0.24
    POSITIVE LOGITS
    -sale
    0.31
    åŀĭä¼ģä¸ļ
    0.29
    æĹ¢åı¯ä»¥
    0.28
    ä¸įä½Ĩ
    0.28
    ä¼ģä¸ļæıIJä¾Ľ
    0.27
    -</
    0.26
    åĬ¨éĿĻ
    0.26
    atar
    0.26
    opr
    0.25
    +</
    0.25
    Activations Density 0.003%

    No Known Activations