© 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. 25-TRANSCODER-HP
    7. 107209
    Prev
    Next
    INDEX
    Explanations

    you

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    .liferay
    -0.28
    çĶ¨æĪ·æıIJä¾Ľ
    -0.28
    æ®ļ
    -0.27
    á¿ĸ
    -0.27
    èĢIJ
    -0.27
     escapes
    -0.26
    è¦ģåĿļæĮģ
    -0.25
    ushi
    -0.25
    管çIJĨæĿ¡ä¾ĭ
    -0.25
     borne
    -0.25
    POSITIVE LOGITS
    èĤ¥
    0.29
     easily
    0.28
    ä½ľçĶ¨
    0.27
    nten
    0.26
    rijk
    0.26
    以为
    0.25
    é¢Ĩ导
    0.25
    æ³Ľ
    0.25
     pro
    0.25
     indent
    0.25
    Activations Density 0.973%

    No Known Activations