© 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. 142652
    Prev
    Next
    INDEX
    Explanations

    at

    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
    dictions
    -0.28
    .TryParse
    -0.28
    adero
    -0.28
     keyValue
    -0.26
    ettes
    -0.26
    ultipart
    -0.25
    SCRI
    -0.25
    ãĤµãĤ¤
    -0.25
     Sized
    -0.25
     backgroundImage
    -0.24
    POSITIVE LOGITS
    -definition
    0.26
    âĶı
    0.25
    è´¯éĢļ
    0.25
     Denied
    0.24
    å¹³æ°ij
    0.24
    ~
    0.24
    ç¾İå¦Ļ
    0.24
    bos
    0.24
    bose
    0.23
     diplomatic
    0.23
    Activations Density 0.170%

    No Known Activations