© 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. 130895
    Prev
    Next
    INDEX
    Explanations

    with

    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
    èı°
    -0.30
    顾
    -0.29
    为ä¸ŃåĽ½
    -0.27
    PGA
    -0.27
    åļ¼
    -0.26
     Maur
    -0.26
    inka
    -0.25
    顧
    -0.25
    chron
    -0.25
    AspNet
    -0.25
    POSITIVE LOGITS
     perfect
    0.39
    åľ°éģĵ
    0.30
     real
    0.27
     final
    0.27
    第ä¸Ģ次
    0.27
    å®Įç¾İçļĦ
    0.27
     reasonable
    0.26
     perfectly
    0.26
    /from
    0.26
     Perfect
    0.26
    Activations Density 9.129%

    No Known Activations