© 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. 88965
    Prev
    Next
    INDEX
    Explanations

    tools, body parts

    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
    ä¸ºçĽ®çļĦ
    -0.27
    Ñĥни
    -0.26
    orio
    -0.26
    à¤Ī
    -0.26
    LY
    -0.26
    iles
    -0.25
     pipelines
    -0.25
    éĺ²èħIJ
    -0.25
    æŁľåı°
    -0.24
    àªĪ
    -0.24
    POSITIVE LOGITS
    æĿ¼
    0.27
    holder
    0.27
    rant
    0.27
    bearer
    0.27
    æIJ¬
    0.26
     placements
    0.26
    hape
    0.26
    æĪ·
    0.25
    æĮª
    0.25
     position
    0.25
    Activations Density 0.071%

    No Known Activations