© 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. 140857
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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
    Not in Any Lists

    No Comments

    Negative Logits
     yet
    -0.29
    .Mapper
    -0.28
    .getBoolean
    -0.26
     Yet
    -0.26
     org
    -0.26
    åĽº
    -0.25
    æľ½
    -0.25
    Yet
    -0.24
     Sloan
    -0.24
    ä»įæľª
    -0.24
    POSITIVE LOGITS
    ä½ĵçİ°åĩº
    0.28
    IDGE
    0.26
    rang
    0.25
    osal
    0.25
    ongan
    0.25
     kre
    0.25
    让æĤ¨
    0.24
    èĩĤ
    0.24
     referring
    0.24
    èĥ½çľĭåĩº
    0.24
    Activations Density 16.588%

    No Known Activations