© 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. 4910
    Prev
    Next
    INDEX
    Explanations

    pear, oxide, -ph, um

    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
    SOLE
    -0.08
    ç«ĭä¸ļ
    -0.08
    ÑĤеÑĢе
    -0.07
    ÑģÑĤви
    -0.07
    ulli
    -0.07
     Dung
    -0.07
    жо
    -0.07
    æłij人
    -0.07
     Lever
    -0.07
    åħ¶å®ĥåªĴä½ĵ
    -0.07
    POSITIVE LOGITS
    æĶ¹
    0.10
    raw
    0.09
     raw
    0.08
    æĶ¹éĢł
    0.08
    æīĵä¸Ģ
    0.08
    Raw
    0.07
    åľ¨ç»ıè¿ĩ
    0.07
    åIJİç»ı
    0.07
     normalization
    0.07
    è§ĦèĮĥåĮĸ
    0.07
    Activations Density 0.445%

    No Known Activations