© 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. 51988
    Prev
    Next
    INDEX
    Explanations

    giving reasons

    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
    водом
    -0.07
    нибÑĥдÑĮ
    -0.07
    æıIJåįĩèĩªå·±çļĦ
    -0.07
    欢è¿İ广大
    -0.07
    åŃ©åŃIJçļĦæĪIJéķ¿
    -0.07
    人çļĦçĶŁæ´»
    -0.07
    产åĵģçļĦçłĶåıij
    -0.07
    æ·±åħ¥åľ°
    -0.07
     }):
    -0.06
     unmist
    -0.06
    POSITIVE LOGITS
    avera
    0.07
    erei
    0.07
    лÑĮкÑĥ
    0.07
    éĺ³åİ¿
    0.06
    etre
    0.06
    ibus
    0.06
    å®ĥæĺ¯
    0.06
    åĪ°
    0.06
    acker
    0.06
     $('[
    0.06
    Activations Density 0.005%

    No Known Activations