© 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. 62828
    Prev
    Next
    INDEX
    Explanations

    crawl

    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
     post
    -0.25
     should
    -0.25
    gr
    -0.25
     standardized
    -0.25
    UC
    -0.25
    åŁº
    -0.24
    post
    -0.24
    æł¼
    -0.24
    .gr
    -0.24
    bearing
    -0.24
    POSITIVE LOGITS
    rement
    0.27
    ushman
    0.26
    FREE
    0.26
    ARAM
    0.26
    gies
    0.25
    appings
    0.25
    insi
    0.25
    VML
    0.25
    rooms
    0.25
    tent
    0.24
    Activations Density 7.816%

    No Known Activations