© 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. 131002
    Prev
    Next
    INDEX
    Explanations

    Code snippets, documentation

    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
    Negative Logits
    ApplicationBuilder
    -0.26
    è¿ĺæľīä»Ģä¹Ī
    -0.26
    lem
    -0.26
     park
    -0.25
     yet
    -0.24
    ãģ©ãģ®ãĤĪãģĨãģª
    -0.23
    resse
    -0.23
    æĺŁå·´
    -0.23
    åĽ½åº¦
    -0.23
    гон
    -0.23
    POSITIVE LOGITS
    æ¯Ľ
    0.27
    æ´»
    0.25
    çŃ¹èµĦ
    0.25
    addChild
    0.25
    亡
    0.24
     Masc
    0.24
    æĸ½
    0.24
    eto
    0.24
    .ToTable
    0.23
    å¹´
    0.23
    Activations Density 14.453%

    No Known Activations