© 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. 128917
    Prev
    Next
    INDEX
    Explanations

    Questions/answers

    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
    éĤ£æł·çļĦ
    -0.34
    fel
    -0.30
    éĤ£æł·
    -0.29
    idden
    -0.26
    éĤ£ä¸ªäºº
    -0.25
     convict
    -0.25
    ween
    -0.25
    两个维æĬ¤
    -0.25
    urous
    -0.25
    éĴĹ
    -0.25
    POSITIVE LOGITS
     accordingly
    0.26
    har
    0.26
     Du
    0.26
    åĸĦ
    0.25
    Du
    0.25
    elo
    0.25
     Dro
    0.25
    sty
    0.24
     sag
    0.24
     consequently
    0.24
    Activations Density 0.008%

    No Known Activations