© 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. 22-TRANSCODER-HP
    7. 110964
    Prev
    Next
    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    eton
    -0.27
    åħļåĴĮ
    -0.26
    é¢Ĩè¡Ķ
    -0.24
     Bones
    -0.24
     Chim
    -0.24
    .twitter
    -0.23
    |R
    -0.23
     yanı
    -0.23
     Wenger
    -0.23
    çĤ¹äºĨçĤ¹å¤´
    -0.23
    POSITIVE LOGITS
    orate
    0.29
    atorial
    0.27
    æĭľ
    0.27
    pite
    0.26
    clearfix
    0.25
    cum
    0.25
    巴士
    0.25
    aits
    0.25
    åĨį
    0.25
    临
    0.24
    Activations Density 0.015%

    No Known Activations