© 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. 107123
    Prev
    Next
    INDEX
    Explanations

    the

    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
     hairs
    -0.26
    _arc
    -0.25
    éĺ³
    -0.24
     arc
    -0.24
    å¤į
    -0.23
    bsites
    -0.23
    ç¡IJ
    -0.23
     inverse
    -0.23
    .ErrorCode
    -0.23
    纶
    -0.23
    POSITIVE LOGITS
    棵æłij
    0.30
     carr
    0.29
    æĭİ
    0.28
    æŀ¯
    0.27
     Arrival
    0.26
    èĢĮæĿ¥
    0.26
    åħ¥ä½ı
    0.24
    æĬµè¾¾
    0.24
    cdb
    0.24
    OfClass
    0.24
    Activations Density 36.023%

    No Known Activations