© 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. 112803
    Prev
    Next
    INDEX
    Explanations

    soil

    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
    绪
    -0.28
    é³Ĭ
    -0.27
    ç¾½æ¯Ľ
    -0.26
    ool
    -0.26
     distraction
    -0.25
    ä¸ĢèĤ¡
    -0.24
    ç¾½
    -0.24
     VOID
    -0.24
    尺度
    -0.24
     mát
    -0.24
    POSITIVE LOGITS
    ceased
    0.25
    enance
    0.25
    uble
    0.25
    å¥ĺ
    0.25
    anh
    0.24
    аÑĤÑĮÑģÑı
    0.24
     endforeach
    0.24
    unger
    0.24
     getLast
    0.24
    riteln
    0.23
    Activations Density 0.037%

    No Known Activations