© 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. 8272
    Prev
    Next
    INDEX
    Explanations

    free

    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
     expense
    -0.31
     costing
    -0.29
     cost
    -0.28
    ç¿Ķ
    -0.28
    æĪIJæľ¬
    -0.28
     quad
    -0.27
    豪
    -0.27
    èĬ±è´¹
    -0.27
    以
    -0.27
    &E
    -0.27
    POSITIVE LOGITS
    ousse
    0.32
    ignet
    0.29
    ãģ¾ãģ¨ãĤģ
    0.27
    ikut
    0.25
    å¹´ä¸ĭåįĬå¹´
    0.25
    é¢ĦåijĬ
    0.25
    ochen
    0.24
     todd
    0.23
     newItem
    0.23
     itemName
    0.23
    Activations Density 0.010%

    No Known Activations