© 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. 14-TRANSCODER-HP
    7. 40122
    Prev
    Next
    INDEX
    Explanations

    Code/Technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Beste
    -0.29
    ä¸ĬåѦ
    -0.27
    æĿ¥çľĭçľĭåIJ§
    -0.26
    äºĮåŃĹ
    -0.24
    éķ¿å¾Ĺ
    -0.24
    ä»Ĭ天å°ıç¼ĸ
    -0.23
    èĤļ
    -0.23
     günd
    -0.23
     Guess
    -0.23
     Og
    -0.23
    POSITIVE LOGITS
    igators
    0.28
     niên
    0.25
    -under
    0.24
    ÑĤан
    0.24
    亿åIJ¨
    0.24
    âĻŃ
    0.23
    çłĶ究ä¸Ńå¿ĥ
    0.23
    íijľ
    0.23
    æ¯Ķ
    0.23
    ASN
    0.23
    Activations Density 1.839%

    No Known Activations