© 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. 63144
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    äºĭåĬ¡
    -0.27
    GroupName
    -0.26
    ocha
    -0.26
    ä¼ł
    -0.26
    short
    -0.26
     char
    -0.24
    çŃ¹
    -0.24
    åįĵ
    -0.24
    wend
    -0.23
    IENCE
    -0.23
    POSITIVE LOGITS
    isers
    0.29
     Browse
    0.28
     bè
    0.28
     acquiring
    0.27
    楫
    0.27
    idis
    0.26
    夫å¦ĩ
    0.26
    alers
    0.24
    ATO
    0.24
    гÑĢамм
    0.24
    Activations Density 20.599%

    No Known Activations

    This feature has no known activations.