© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30358
    Prev
    Next
    INDEX
    Explanations

    Google keep OCR

    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
    åį³æĹ¥
    -0.08
    ardown
    -0.08
    acula
    -0.07
    estand
    -0.07
    ìĶ©
    -0.07
    aku
    -0.07
    åIJĦè¡Į
    -0.07
    uwe
    -0.06
    uas
    -0.06
    -offset
    -0.06
    POSITIVE LOGITS
    }}{{
    0.08
    æĿ¥è¯´
    0.08
    ä¹Łå¥½
    0.07
    ãģ¨ãģ¯ãģĦãģĪ
    0.07
    ä¹Łä¸įä¾ĭå¤ĸ
    0.07
    æĿ¥è¯´æĺ¯
    0.07
    ä¹Łç½¢
    0.07
    éĺħè¯»æľ¬æĸĩåīį
    0.07
    ìłģìľ¼ë¡ľëĬĶ
    0.07
    å±ĤéĿ¢ä¸Ĭ
    0.07
    Activations Density 0.017%

    No Known Activations