© 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. 31-TRANSCODER-HP
    7. 19957
    Prev
    Next
    INDEX
    Explanations

    medical texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     fle
    -0.32
     speaking
    -0.31
    fl
    -0.30
    spe
    -0.30
     abstract
    -0.29
    Spe
    -0.28
     oper
    -0.27
    æĬ½è±¡
    -0.27
    dle
    -0.27
     fil
    -0.27
    POSITIVE LOGITS
     modes
    0.35
    Modes
    0.34
    æµĭè¯ķ
    0.32
     Modes
    0.31
    ette
    0.31
    缸åħ³ä¿¡æģ¯
    0.30
    TestMethod
    0.30
    _modes
    0.30
    modes
    0.29
    管çIJĨ模å¼ı
    0.29
    Activations Density 0.378%

    No Known Activations