© 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. 131022
    Prev
    Next
    INDEX
    Explanations

    Programming code

    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
    berries
    -0.28
    ilver
    -0.27
    .jackson
    -0.25
    cket
    -0.25
    %E
    -0.24
    ä¸įèĥ½ä¸ºç©º
    -0.24
     intents
    -0.24
     Implement
    -0.24
    (sem
    -0.23
    ä¼Łå¤§å¤įåħ´
    -0.23
    POSITIVE LOGITS
     sour
    0.27
     loved
    0.25
    AH
    0.25
     source
    0.24
    oub
    0.24
    rible
    0.24
    .source
    0.24
    has
    0.24
    ht
    0.23
    oug
    0.23
    Activations Density 0.027%

    No Known Activations