© 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. 18004
    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
    åħī
    -0.29
     communities
    -0.28
    owering
    -0.27
    fte
    -0.26
    TION
    -0.26
     Ste
    -0.25
     channels
    -0.25
    евиÑĩ
    -0.25
    arith
    -0.25
     caves
    -0.25
    POSITIVE LOGITS
    lyn
    0.30
     prol
    0.28
    èĭ¦æģ¼
    0.25
     Suzanne
    0.25
    uspend
    0.25
     elabor
    0.24
    éĩįåŀĭ
    0.24
     ur
    0.24
    trs
    0.24
    å¡ĺ
    0.24
    Activations Density 0.305%

    No Known Activations