© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 130380
    Prev
    Next
    INDEX
    Explanations

    Code and formal documents

    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
    \Form
    -0.28
    工夫
    -0.27
     fic
    -0.26
    uple
    -0.26
    æĿ¥çļĦ
    -0.26
    ä¸ĵèģĮ
    -0.26
    åľ¨è¿ĩ渡
    -0.25
    zel
    -0.25
    owment
    -0.24
    à¤ĺ
    -0.24
    POSITIVE LOGITS
     Portions
    0.28
     Dich
    0.26
    sar
    0.25
    éĽªèĬ±
    0.24
    褫
    0.23
     ÅŁeklinde
    0.23
    æİĴè¡Įæ¦ľ
    0.23
     Approval
    0.23
    syn
    0.22
    .pattern
    0.22
    Activations Density 0.028%

    No Known Activations