© 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. 99254
    Prev
    Next
    INDEX
    Explanations

    Cause and effect

    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
    opard
    -0.27
     weir
    -0.26
     hated
    -0.26
    ég
    -0.24
     outraged
    -0.24
     inaug
    -0.24
    contri
    -0.24
     ousted
    -0.23
     furious
    -0.23
    ç»·
    -0.23
    POSITIVE LOGITS
    .us
    0.29
     general
    0.28
    submenu
    0.27
    ä¸ĢèĪ¬æĺ¯
    0.25
    ä¸Ģæĺ¯
    0.25
     ['.
    0.24
    åīįä¸ī
    0.24
    chooser
    0.24
    .general
    0.24
    ajs
    0.24
    Activations Density 0.016%

    No Known Activations