© 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. 8486
    Prev
    Next
    INDEX
    Explanations

    punctuation and stop words

    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
    å¾Ī满æĦı
    -0.27
    好æ¶Īæģ¯
    -0.26
    sure
    -0.25
    lington
    -0.25
    หมาย
    -0.25
    åIJĪä½ľåįıè®®
    -0.24
    -risk
    -0.24
    .fs
    -0.24
     Tomorrow
    -0.24
    æĹ¥è®¯
    -0.24
    POSITIVE LOGITS
    rette
    0.27
     ç»ĵ
    0.26
    æķĻä½ł
    0.26
    ocr
    0.26
     hall
    0.25
    ä¸Ŀ
    0.25
    åIJĪ
    0.25
    opper
    0.24
    è¾°
    0.24
     orth
    0.24
    Activations Density 0.075%

    No Known Activations