© 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. 44548
    Prev
    Next
    INDEX
    Explanations

    central, lean, apparent, globe, free

    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
    åıĪ好
    -0.08
    å¹²æ¶ī
    -0.08
    æ´ĭæ´ĭ
    -0.07
     sana
    -0.07
    åı¯æĢľ
    -0.07
    å¤§æľ¬
    -0.07
    çŃĸçķ¥
    -0.07
    chine
    -0.07
    áĬĵ
    -0.07
    uris
    -0.07
    POSITIVE LOGITS
    è¿Ļæīįæĺ¯
    0.14
    æīįæĺ¯çľŁæŃ£çļĦ
    0.12
    æīįæĺ¯
    0.11
     rather
    0.10
    èĢĮéĿŀ
    0.09
    èĢĮä¸įæĺ¯
    0.09
    æīįæĺ¯æľĢ
    0.09
    æīį对
    0.09
    羣æŃ£
    0.08
     instead
    0.08
    Activations Density 0.036%

    No Known Activations