© 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. 142644
    Prev
    Next
    INDEX
    Explanations

    coding

    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
    iges
    -0.30
    äºĭ件
    -0.29
    Event
    -0.28
    ä¹Łä¸įæĺ¯
    -0.27
    ä¸įæĺ¯
    -0.27
    event
    -0.26
    è¿Ļä¸Ģå¹´
    -0.26
     event
    -0.26
    ement
    -0.25
    ika
    -0.25
    POSITIVE LOGITS
    ndx
    0.34
     ObjectOutputStream
    0.28
    onaut
    0.28
    åıijçİ°äºĨ
    0.25
    catid
    0.25
    ohl
    0.25
     Tradable
    0.25
    abcdefghijkl
    0.25
     sod
    0.25
     numbers
    0.24
    Activations Density 21.837%

    No Known Activations