© 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. 130893
    Prev
    Next
    INDEX
    Explanations

    capital

    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
    ży
    -0.27
    ket
    -0.26
    proof
    -0.25
     tid
    -0.25
    isd
    -0.24
     parallel
    -0.24
    èį¯
    -0.24
     parallels
    -0.24
    à¸Ľà¸£à¸°à¸ģà¸Ńà¸ļ
    -0.24
    æł¡
    -0.24
    POSITIVE LOGITS
    èĨº
    0.30
    lescope
    0.28
    大è¡Ĺ
    0.28
    edly
    0.27
    awy
    0.25
    åIJĦè¡ĮåIJĦ
    0.25
    roker
    0.24
     Burk
    0.24
    为é¦ĸ
    0.24
    |RF
    0.24
    Activations Density 3.610%

    No Known Activations