© 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. 111181
    Prev
    Next
    INDEX
    Explanations

    Explaining something

    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
    丰满
    -0.28
     vagina
    -0.28
    èĤĽ
    -0.27
     tits
    -0.27
     anus
    -0.27
    夹
    -0.26
    æľĢ强
    -0.25
    xbb
    -0.24
    bsolute
    -0.24
    客è§Ĥ
    -0.24
    POSITIVE LOGITS
     why
    0.44
    为ä»Ģä¹Ī
    0.39
    why
    0.35
    çĤºä»Ģ麼
    0.34
     Why
    0.33
    éļ¾æĢª
    0.33
    为ä½ķ
    0.32
    Why
    0.31
    ãģªãģľ
    0.31
    ineTransform
    0.31
    Activations Density 0.013%

    No Known Activations