© 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. 59944
    Prev
    Next
    INDEX
    Explanations

    interesting thing

    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
    zysta
    -0.08
    走好
    -0.08
    tent
    -0.08
     nhu
    -0.08
    ims
    -0.07
    çļĦç¡®æĺ¯
    -0.07
    åĭī
    -0.07
    Ñģловно
    -0.07
    æĭĻ
    -0.07
    ARING
    -0.07
    POSITIVE LOGITS
    åľ¨äºİ
    0.17
    ä¹ĭå¤Ħåľ¨äºİ
    0.16
    å°±åľ¨äºİ
    0.15
    åľ¨æĸ¼
    0.13
    åħ³éĶ®æĺ¯
    0.12
    åħ³éĶ®åľ¨äºİ
    0.12
     заклÑİÑĩаеÑĤÑģÑı
    0.11
    ä¸įåIJĮçļĦæĺ¯
    0.10
    ä¹ĭå¤Ħ
    0.10
    æľĢåħ³éĶ®
    0.10
    Activations Density 0.316%

    No Known Activations