© 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. 41775
    Prev
    Next
    INDEX
    Explanations

    just/unjust

    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
    åħ¨åľº
    -0.27
    recent
    -0.26
    aeda
    -0.25
    _managed
    -0.25
    ETO
    -0.24
     Fury
    -0.24
    unden
    -0.24
    åij¨åĽ´çļĦ
    -0.24
     Deadly
    -0.24
    åįĬ个
    -0.23
    POSITIVE LOGITS
    çī©æµģåħ¬åı¸
    0.28
    ies
    0.27
    seek
    0.26
    ãģĭãĤĭ
    0.25
    ãģ½
    0.25
    æķĽ
    0.25
    .dismiss
    0.25
    à´Ļ
    0.25
    åĽĽæĸ¹
    0.25
    æ³Ľ
    0.24
    Activations Density 1.873%

    No Known Activations