© 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. 59806
    Prev
    Next
    INDEX
    Explanations

    two or more

    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
    æĹ¢åı¯
    -0.09
    aisu
    -0.09
    astiche
    -0.08
    ä»İåħ¶
    -0.08
    软硬
    -0.08
    _except
    -0.08
     &_
    -0.08
    ORK
    -0.07
    ç½®ä¹ĭ
    -0.07
    ÙĨÙĩ
    -0.07
    POSITIVE LOGITS
     ÑģобÑģÑĤвенно
    0.08
    ä¹Łç§°ä¸º
    0.07
    former
    0.07
     whereas
    0.07
     predominant
    0.07
     relatively
    0.07
    主è¦ģ
    0.06
     corresponds
    0.06
     bulk
    0.06
    顾åIJįæĢĿä¹ī
    0.06
    Activations Density 0.164%

    No Known Activations