© 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. 14-TRANSCODER-HP
    7. 41766
    Prev
    Next
    INDEX
    Explanations

    Medical texts/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æİ¥
    -0.27
    交
    -0.27
     broad
    -0.26
    że
    -0.26
    LOC
    -0.25
     marginal
    -0.25
    æ¯Ľ
    -0.25
    å¿ĻçĿĢ
    -0.25
    èĽĭçĻ½
    -0.24
    ç¼´
    -0.24
    POSITIVE LOGITS
    æ´Ħ
    0.27
    åįİå°Ķ
    0.27
    panies
    0.27
    åıĸåĨ³
    0.27
    éĺ¿å¯Į
    0.27
    Rated
    0.26
    è¡©
    0.26
    éĵ¨
    0.26
    entially
    0.26
     Eag
    0.26
    Activations Density 1.372%

    No Known Activations