© 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. 27-TRANSCODER-HP
    7. 9644
    Prev
    Next
    INDEX
    Explanations

    place names and programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    å°ıå°ı
    -0.29
    ç»Ļä½łä»¬
    -0.27
    nish
    -0.27
    çļĦ人æĿ¥è¯´
    -0.27
    人家
    -0.26
     Engineer
    -0.26
    广æĴŃçĶµè§Ĩ
    -0.25
    =";↵
    -0.25
    åħ¨åªĴä½ĵ
    -0.25
    ãģ¤ãģ®
    -0.24
    POSITIVE LOGITS
    æŁĶ
    0.28
     bog
    0.28
    awks
    0.27
    åı¯è¡Į
    0.27
    æį£
    0.26
     DEF
    0.26
    è¯Ŀé¢ĺ
    0.25
    HIR
    0.25
     mil
    0.25
     rig
    0.25
    Activations Density 0.012%

    No Known Activations