© 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. 873
    Prev
    Next
    INDEX
    Explanations

    non-

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸Ĭ个
    -0.07
    czyn
    -0.07
    ç»ı
    -0.07
    дин
    -0.06
    çIJĨæĥ³çļĦ
    -0.06
    ?type
    -0.06
    ç»ıåıĹ
    -0.06
     Hope
    -0.06
    å¸Į
    -0.06
    —the
    -0.06
    POSITIVE LOGITS
    æĪijçļĦç¥Ŀç¦ı
    0.07
    ³
    0.07
    yles
    0.07
    aat
    0.07
    å·¥ä½ľéĩįçĤ¹
    0.07
    åıįå¤įåıijä½ľ
    0.07
    کار
    0.07
    éĭĴ
    0.07
    -collapse
    0.07
    è¶ĬæĿ¥è¶Ĭè¿ij
    0.07
    Activations Density 0.033%

    No Known Activations