© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 34981
    Prev
    Next
    INDEX
    Explanations

    interface actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    çĶ¨äºİ
    -0.10
    çļĦä¸ĢåĪĩéĥ½
    -0.10
    è´¹çĶ¨çĶ±
    -0.09
    åĨħ容çĶ±
    -0.09
    çĶ¨ä»¥
    -0.09
    çĶ¨äºİæ²»çĸĹ
    -0.09
    ä¼ļè®®çĶ±
    -0.08
    indle
    -0.08
     untuk
    -0.08
    çĶ¨æĿ¥
    -0.08
    POSITIVE LOGITS
     biais
    0.10
    çŃīæīĭ段
    0.10
    ä¹ĭæīĭ
    0.09
    çŃīæĸ¹å¼ı
    0.09
     alone
    0.08
    æīĭ段
    0.08
    çļĦæĸ¹å¼ı
    0.08
    means
    0.08
     means
    0.08
     heen
    0.08
    Activations Density 1.329%

    No Known Activations