© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 9-TRANSCODER-HP
    7. 29192
    Prev
    Next
    INDEX
    Explanations

    code/version numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     trần
    -0.29
    帮åĬ©ä¼ģä¸ļ
    -0.28
    riel
    -0.27
    éĵ¨
    -0.26
    amba
    -0.25
    奶
    -0.25
    abee
    -0.25
    olph
    -0.25
     cuanto
    -0.24
    为ä¼ģä¸ļ
    -0.24
    POSITIVE LOGITS
    :o
    0.25
    ogra
    0.25
    lined
    0.24
     tuyến
    0.24
    odate
    0.24
    /stats
    0.23
    äºĨ解åĪ°
    0.23
    æ¡¡
    0.23
    æĺ¥æĻļ
    0.23
     Lock
    0.23
    Activations Density 23.139%

    No Known Activations