© 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. 7935
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    adius
    -0.31
    å¦Ĥæŀľæľī
    -0.27
     protector
    -0.27
    ä¸ĩ个
    -0.25
    .fn
    -0.25
    acker
    -0.25
    ength
    -0.25
    printStats
    -0.25
    ndon
    -0.24
    abeled
    -0.23
    POSITIVE LOGITS
    Operand
    0.27
    ä¸»åľº
    0.25
    æİ¥ä¸ĭæĿ¥
    0.25
    称ä¹ĭ
    0.25
     ÑģиÑĤ
    0.25
    说æĺ¯
    0.24
    ÙĨÙĤ
    0.24
    ÅŁÄ±k
    0.24
     Undert
    0.24
    è¿Ļ座
    0.23
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.