© 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. 141615
    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
    TON
    -0.26
    eval
    -0.25
    makt
    -0.24
    agog
    -0.24
    esch
    -0.24
    earing
    -0.24
    icrous
    -0.24
    iang
    -0.23
    深度
    -0.23
    ionario
    -0.23
    POSITIVE LOGITS
    pine
    0.27
    orman
    0.26
    åIJİæĿ¥
    0.25
    æ¯ĽåŃĶ
    0.25
     prematurely
    0.24
     hail
    0.24
     transpose
    0.24
     later
    0.24
    å¾Īå¤ļæľĭåıĭ
    0.24
    ODO
    0.24
    Activations Density 2.242%

    No Known Activations

    This feature has no known activations.