© 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. 35-TRANSCODER-HP
    7. 38761
    Prev
    Next
    INDEX
    Explanations

    lo

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ï¼ŁãĢį
    -0.29
    ä¹Łæ¯Ķè¾ĥ
    -0.29
    èļķ
    -0.27
    ï¼Ł”
    -0.27
     ÑĢеализ
    -0.26
    ÑĢаз
    -0.25
    麽
    -0.24
    缮çļĦ
    -0.23
    ä¹Łä¸įæķ¢
    -0.23
    ç½®ãģĦãģ¦
    -0.23
    POSITIVE LOGITS
    !
    0.52
     stu
    0.36
     stag
    0.35
     stad
    0.35
     standard
    0.34
     sperma
    0.33
     sc
    0.33
     store
    0.33
     sport
    0.33
     Shops
    0.33
    Activations Density 4.443%

    No Known Activations