© 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. 62981
    Prev
    Next
    INDEX
    Explanations

    large numbers

    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
    deal
    -0.26
    weigh
    -0.26
    ged
    -0.25
    ubi
    -0.24
    gar
    -0.24
    guid
    -0.24
    -gap
    -0.24
    gó
    -0.24
     deg
    -0.24
    çļĦ人çĶŁ
    -0.23
    POSITIVE LOGITS
    å¹´æĿ¥
    0.28
    ä¼Ļ
    0.28
    年以æĿ¥
    0.26
    ç½¢äºĨ
    0.26
    HING
    0.26
    adr
    0.25
    errated
    0.25
    åİ
    0.24
    roys
    0.24
     initialValue
    0.24
    Activations Density 4.233%

    No Known Activations