© 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. 129173
    Prev
    Next
    INDEX
    Explanations

    itis

    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
    åĴĮæľįåĬ¡
    -0.26
    smith
    -0.25
    uzzle
    -0.24
    禺
    -0.24
    oze
    -0.24
    eee
    -0.24
    odiac
    -0.24
    ÄĽ
    -0.24
    oen
    -0.24
    alach
    -0.24
    POSITIVE LOGITS
    ERVE
    0.26
    s
    0.26
    æĤ£èĢħçļĦ
    0.25
     dorsal
    0.25
    urgeon
    0.25
    ief
    0.25
    ÅĽÄĩ
    0.24
    æĤ£èĢħ
    0.24
    ãģ£ãģįãĤĬ
    0.23
     effort
    0.23
    Activations Density 0.169%

    No Known Activations