© 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. 20-TRANSCODER-HP
    7. 107562
    Prev
    Next
    INDEX
    Explanations

    Code and brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iform
    -0.28
    åİħ
    -0.27
    缮çļĦåľ¨äºİ
    -0.25
    à¸ļาย
    -0.25
    otti
    -0.25
     (\
    -0.25
    .IsSuccess
    -0.25
    3
    -0.24
    ä»ĸ们ä¼ļ
    -0.24
    enza
    -0.24
    POSITIVE LOGITS
    ë²
    0.26
    Anonymous
    0.26
    éĤ£äºĽ
    0.25
     Draws
    0.25
    pointer
    0.25
    ä¸Ńåįİ
    0.24
     Printing
    0.24
    é¼İ
    0.24
    (pointer
    0.24
     printable
    0.24
    Activations Density 0.531%

    No Known Activations