© 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. 27-TRANSCODER-HP
    7. 8939
    Prev
    Next
    INDEX
    Explanations

    pig

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¿«æĬ¥
    -0.28
    佶
    -0.27
    责任ç¼ĸè¾ij
    -0.26
    erializer
    -0.24
    inker
    -0.24
    ä»°
    -0.23
    大åŁİå¸Ĥ
    -0.23
    éĽĨåĽ¢èĤ¡ä»½
    -0.23
    æĪ·ç±į
    -0.23
     Bik
    -0.23
    POSITIVE LOGITS
    culate
    0.29
    ieties
    0.27
    arine
    0.27
    etros
    0.27
    uments
    0.26
    ones
    0.26
    oints
    0.26
    ared
    0.26
    systems
    0.26
    ruise
    0.26
    Activations Density 0.051%

    No Known Activations