© 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. 20-TRANSCODER-HP
    7. 140841
    Prev
    Next
    INDEX
    Explanations

    Text separators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vest
    -0.29
    ооÑĢ
    -0.27
    ansom
    -0.25
    好è¿IJ
    -0.25
    oph
    -0.24
    çĶ¨åĵģ
    -0.23
    è¿ĻäºĽä¸ľè¥¿
    -0.23
    ngrx
    -0.23
    è¿ŀ线
    -0.23
    缸åħ³åĨħ容
    -0.23
    POSITIVE LOGITS
    @(
    0.28
    Sharing
    0.25
     absolute
    0.25
     darn
    0.24
    logue
    0.24
    å®ŀè·µç»ıéªĮ
    0.24
    )==
    0.24
    ç»Ŀ对
    0.24
     absol
    0.24
    ritable
    0.23
    Activations Density 95.557%

    No Known Activations