© 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. 20-TRANSCODER-HP
    7. 62894
    Prev
    Next
    INDEX
    Explanations

    possibilities and truncated sentences

    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
    _frm
    -0.26
    ç»Ŀä¸į
    -0.25
    è´Łæĭħ
    -0.25
    æ³¥
    -0.25
    åıĸå¾ĹäºĨ
    -0.25
     Riding
    -0.24
    because
    -0.24
    ADER
    -0.24
    æĪIJ为äºĨ
    -0.24
     because
    -0.24
    POSITIVE LOGITS
    /null
    0.29
    -sc
    0.28
    大éĻĨ
    0.26
    大éĻ¸
    0.25
    æľįåĬ¡ä¸ļ
    0.25
    \Entities
    0.24
     certain
    0.24
    æĹłå£°
    0.24
     Certain
    0.24
    (cin
    0.24
    Activations Density 26.663%

    No Known Activations