© 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. 7943
    Prev
    Next
    INDEX
    Explanations

    eclipse, coding, reports

    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
    rain
    -0.28
    ução
    -0.27
    -issue
    -0.26
    ç»ıæŁ¥
    -0.26
     Equip
    -0.26
    鼨
    -0.26
    çķ¹
    -0.26
    ãģ»ãģĨ
    -0.25
    Equip
    -0.25
     root
    -0.25
    POSITIVE LOGITS
     rendez
    0.28
    Celebr
    0.28
     spectacle
    0.26
    å¤ĸè§Ĥ
    0.25
    ç²¾ç¥ŀ
    0.25
    *pow
    0.25
    è²Į
    0.25
    çļĦ身影
    0.25
     condo
    0.24
    úng
    0.24
    Activations Density 0.005%

    No Known Activations