© 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. 7459
    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
    AGMA
    -0.31
    è¡ĮåĬ¨è®¡åĪĴ
    -0.29
    &action
    -0.28
    ä¸į好
    -0.28
    çIJĨ
    -0.28
    ç»ĻåŃ©åŃIJ
    -0.26
    è½²
    -0.25
    ðŁijĭ
    -0.24
    CRT
    -0.24
    legt
    -0.24
    POSITIVE LOGITS
    .cond
    0.30
    spot
    0.29
    Cond
    0.28
    caught
    0.27
    uming
    0.27
     Cond
    0.26
    adays
    0.26
    大è¡Ĺ
    0.26
    (cond
    0.26
    -cond
    0.25
    Activations Density 0.035%

    No Known Activations

    This feature has no known activations.