© 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. 131137
    Prev
    Next
    INDEX
    Explanations

    Research reports and studies

    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
    éĩĮçļĦ
    -0.27
    ENDOR
    -0.26
    STS
    -0.25
     ...(
    -0.25
    igi
    -0.25
    rac
    -0.24
     ESP
    -0.24
    vak
    -0.24
    è¹Ļ
    -0.24
    èĩªå¸¦
    -0.23
    POSITIVE LOGITS
     tÃŃn
    0.27
    详
    0.26
    å¢ĥ
    0.26
     refer
    0.26
    åĩ¿
    0.25
    åħ¥ä½ı
    0.25
    äºĨ好åĩł
    0.25
    éģĹæĨ¾
    0.25
     joke
    0.25
    [at
    0.24
    Activations Density 11.588%

    No Known Activations