© 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. 111071
    Prev
    Next
    INDEX
    Explanations

    studies

    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
    èį¡
    -0.30
    exc
    -0.28
    season
    -0.28
    -exc
    -0.25
    _season
    -0.25
    Exc
    -0.25
    åĴĮåıijå±ķ
    -0.24
    ç§ijæĬĢè¿ĽæŃ¥
    -0.24
    erv
    -0.24
     Season
    -0.24
    POSITIVE LOGITS
     focus
    0.32
    focus
    0.28
    èģļçĦ¦
    0.27
     Kane
    0.27
    .setFocus
    0.26
    .focus
    0.26
     focusing
    0.25
     Focus
    0.25
     foc
    0.25
    IMIT
    0.25
    Activations Density 0.038%

    No Known Activations