© 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. 140820
    Prev
    Next
    INDEX
    Explanations

    briefly

    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
    æĬ¬å¤´
    -0.25
    è¿ĺå°Ĩ
    -0.24
    æķ°æį®æĺ¾ç¤º
    -0.24
    %C
    -0.24
    ç»ĵæĿŁåIJİ
    -0.23
     SOLD
    -0.23
    éĥ¨åĪĨåĨħ容
    -0.23
    確
    -0.23
    Data
    -0.23
     MAN
    -0.23
    POSITIVE LOGITS
    éĻ¤éĿŀ
    0.28
    erp
    0.26
    tures
    0.26
     ($)
    0.26
    yms
    0.25
     cad
    0.25
    éļĪ
    0.24
    nı
    0.24
     Nil
    0.24
    ughters
    0.24
    Activations Density 7.504%

    No Known Activations