© 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. 141474
    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
    etheless
    -0.24
    骥
    -0.24
    ç½ijç«Ļ建设
    -0.24
    _Des
    -0.23
     wohl
    -0.23
    ä»ĸå·²ç»ı
    -0.23
    gages
    -0.23
    cente
    -0.23
    ãĢħ
    -0.23
    igma
    -0.23
    POSITIVE LOGITS
    æŶ任
    0.28
    å³Ń
    0.26
    ...",↵
    0.26
    ..."↵
    0.26
    æĭīä¸ģ
    0.25
    -time
    0.25
    å¸Ľ
    0.25
    éĤ£å¤©
    0.25
    æ²±
    0.24
    è¾Ł
    0.24
    Activations Density 0.242%

    No Known Activations

    This feature has no known activations.