© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6400
    Prev
    Next
    INDEX
    Explanations

    computer code

    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
    replacement
    -0.31
     replacement
    -0.29
     replacements
    -0.28
     Replacement
    -0.26
     replacing
    -0.26
    è¡¥
    -0.25
    çªľ
    -0.24
    ertools
    -0.24
    ONGO
    -0.24
    este
    -0.24
    POSITIVE LOGITS
     laps
    0.27
     inferred
    0.27
    æĢ»çļĦ
    0.27
    æĢ»çļĦæĿ¥è¯´
    0.26
    ToEnd
    0.26
    burgh
    0.25
    convertView
    0.25
     Climate
    0.24
    anuts
    0.24
    ç«ĭæ³ķ
    0.24
    Activations Density 0.003%

    No Known Activations