© 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. 12-TRANSCODER-HP
    7. 24070
    Prev
    Next
    INDEX
    Explanations

    Legal, medical, academic texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ä¸ī次
    -0.26
    åŃ
    -0.26
    æĪIJ为ä¸ŃåĽ½
    -0.25
    å¼Ģ头
    -0.25
    ä¸īæĸ¹
    -0.24
     Yates
    -0.24
    ä¹Łéļıä¹ĭ
    -0.24
    éĻĤ
    -0.23
     ESA
    -0.23
    建议
    -0.23
    POSITIVE LOGITS
    éķ¿çŁŃ
    0.29
    nero
    0.26
    -commercial
    0.26
     cis
    0.26
    contra
    0.26
     mbox
    0.26
    Updates
    0.25
    é«ĺåĩº
    0.25
    asca
    0.25
    æ®ģ
    0.24
    Activations Density 0.001%

    No Known Activations