© 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. 107029
    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
    Than
    -0.27
    )..
    -0.25
    _fil
    -0.24
    .tom
    -0.24
    ÙħÙĬز
    -0.24
    åħ¼é¡¾
    -0.23
    svp
    -0.23
     sez
    -0.23
    ä¸ŃéĢĶ
    -0.23
    iddles
    -0.23
    POSITIVE LOGITS
    å¹²éĥ¨
    0.29
    ç»Ĭ
    0.27
    -issue
    0.26
    or
    0.26
    æīĵå·¥
    0.25
    åħ¬åħ±èµĦæºIJ
    0.24
    åħ¬çĶ¨
    0.24
    è°±
    0.24
    å¹³æ°ij
    0.23
    çİĭèĢħ
    0.23
    Activations Density 11.475%

    No Known Activations

    This feature has no known activations.