© 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. 22003
    Prev
    Next
    INDEX
    Explanations

    medical wounds

    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
     Sed
    -0.33
    nen
    -0.29
     sed
    -0.29
    å°½åı¯èĥ½
    -0.27
    sed
    -0.27
    æĻºåĬĽ
    -0.27
    IMENT
    -0.26
    /bus
    -0.26
    ç²Ĵ
    -0.25
    è¿IJåĬ¨
    -0.25
    POSITIVE LOGITS
     bases
    0.34
    伤åı£
    0.32
    çĸ®
    0.31
    湿润
    0.30
     base
    0.29
    æ´Ĺæīĭ
    0.29
     wound
    0.28
    basis
    0.28
     basis
    0.27
    èĤĮèĤ¤
    0.27
    Activations Density 0.005%

    No Known Activations