© 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. 129245
    Prev
    Next
    INDEX
    Explanations

    Current events/times

    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
    Not in Any Lists

    No Comments

    Negative Logits
    åŃĶ
    -0.27
     tud
    -0.27
     st
    -0.26
    macros
    -0.26
     Conduct
    -0.25
     Interview
    -0.25
    ³³³
    -0.24
    styl
    -0.24
    åħ·æľīä¸Ģå®ļ
    -0.23
    Interview
    -0.23
    POSITIVE LOGITS
     tomorrow
    0.26
    .appendTo
    0.26
    astic
    0.25
    éŀŃ
    0.24
    æĺİ天
    0.24
    asy
    0.24
    çĮĽ
    0.23
     ниже
    0.23
    peon
    0.23
    mons
    0.23
    Activations Density 0.003%

    No Known Activations