© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 3520
    Prev
    Next
    INDEX
    Explanations

    connections between systems

    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
    è·Łåħļ
    -0.08
    人被
    -0.08
     ìĤ¬íķŃìĿĢ
    -0.08
    åı¯ä»¥ä½ľä¸º
    -0.07
    .cgi
    -0.07
    被æĬĵ
    -0.07
    人æĺ¯
    -0.07
    _FOREACH
    -0.07
    ä¸įä½ıäºĨ
    -0.07
    ÑĢази
    -0.07
    POSITIVE LOGITS
    客æĪ·æıIJä¾Ľ
    0.10
    çĤ¹è¿Ľè¡Į
    0.09
    ç³»ç»Łè¿Ľè¡Į
    0.09
    æĥħåĨµè¿Ľè¡Į
    0.09
    ä¸Ńæ·»åĬł
    0.09
    æīĢçŁ¥
    0.08
    人åijĺè¿Ľè¡Į
    0.08
    ä¿¡æģ¯è¿Ľè¡Į
    0.08
    åģļäºĨä¸Ģ个
    0.08
    çĶ¨æĪ·æıIJä¾Ľ
    0.08
    Activations Density 0.018%

    No Known Activations