© 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. 12-TRANSCODER-HP
    7. 23996
    Prev
    Next
    INDEX
    Explanations

    Wound depth and thickness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    å¹´ä¹ĭ
    -0.33
     Insider
    -0.32
    è´¯
    -0.31
    TE
    -0.27
    æİ¥èijĹ
    -0.25
    ç´§
    -0.25
    äºĽä»Ģä¹Ī
    -0.25
     Kemp
    -0.24
    åĨįçĶŁèĥ½æºIJ
    -0.24
    两æīĭ
    -0.24
    POSITIVE LOGITS
    ivor
    0.28
     victim
    0.26
    ulary
    0.25
    andex
    0.25
    çijĹ
    0.25
     writable
    0.25
     thumbs
    0.25
    aac
    0.24
    iciar
    0.24
    acci
    0.24
    Activations Density 0.001%

    No Known Activations