© 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. 41523
    Prev
    Next
    INDEX
    Explanations

    Updates, revisions or modifications

    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
    ennis
    -0.26
     Fifth
    -0.25
     eens
    -0.25
    æĤį
    -0.25
    ç¨İçİĩ
    -0.24
    æĮ¹
    -0.24
     Junk
    -0.24
    ä¸ŃåĽ½ä¼łç»Ł
    -0.24
    æĸ°éĹ»è®°èĢħ
    -0.23
     mediocre
    -0.23
    POSITIVE LOGITS
    chio
    0.26
    idores
    0.25
    kill
    0.24
    ÙĪÙĤ
    0.24
    antine
    0.24
    ?,?,?,?,
    0.23
    iones
    0.23
    æ§İ
    0.23
    çļĦç¼ĺ
    0.23
    prech
    0.23
    Activations Density 0.098%

    No Known Activations