© 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. 34985
    Prev
    Next
    INDEX
    Explanations

    conventionally then descriptor

    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
    ä»ħæѤ
    -0.09
     foregoing
    -0.08
    ä¸ĢæĿ¥
    -0.07
    èĭ¥èĥ½
    -0.07
    æľĢæĸ°è¯Ħ论
    -0.07
    åīįè¿°
    -0.07
    лко
    -0.07
    пÑĢа
    -0.07
    æĥŁæľī
    -0.07
    lyph
    -0.07
    POSITIVE LOGITS
     generally
    0.06
    ãĤĦãģĻ
    0.06
    åıĹåĪ°
    0.06
     conosc
    0.06
    çŀ
    0.06
     rud
    0.06
    è¨ĵ
    0.06
    æĹ©èµ·
    0.06
    å°¤åħ¶æĺ¯åľ¨
    0.06
    asn
    0.06
    Activations Density 0.067%

    No Known Activations