© 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. 34847
    Prev
    Next
    INDEX
    Explanations

    shots or player

    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
    俱ä¹IJéĥ¨
    -0.07
    å½·
    -0.07
    plice
    -0.07
    dio
    -0.07
    beck
    -0.07
    åıĪ称为
    -0.07
    koop
    -0.07
    æĪĸ以
    -0.07
    åijĬ
    -0.06
    çĶļèĩ³æ¯Ķ
    -0.06
    POSITIVE LOGITS
     بدÙĦ
    0.08
     misunderstood
    0.08
     misrepresented
    0.07
    vi
    0.07
    ä¸įå½ĵ
    0.07
    _cache
    0.07
    coni
    0.07
     instead
    0.07
    å£ģ
    0.07
    æĽ´å¤ļä¿¡æģ¯
    0.07
    Activations Density 0.003%

    No Known Activations