© 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. 44390
    Prev
    Next
    INDEX
    Explanations

    fruit

    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
    å¾Ĺ人
    -0.07
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.07
    Rep
    -0.07
    cef
    -0.07
    äºĭ
    -0.07
     wast
    -0.07
    ÐĶС
    -0.06
    å·¥
    -0.06
    %E
    -0.06
    åij¼
    -0.06
    POSITIVE LOGITS
    å«¡
    0.08
    eid
    0.08
    roller
    0.07
    ooter
    0.07
    eme
    0.07
    lai
    0.07
    æĪij们çļĦå·¥ä½ľ
    0.07
    YRO
    0.07
    主è¦ģç»ıèIJ¥
    0.07
    IDGET
    0.06
    Activations Density 0.009%

    No Known Activations