© 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. 8175
    Prev
    Next
    INDEX
    Explanations

    year, sector, rankings, projects

    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
    åį«åģ¥å§Ķ
    -0.08
    æľªå¿ħ
    -0.07
    åģ¥åº·ä¸ŃåĽ½
    -0.07
    赦
    -0.07
    大湾åĮº
    -0.07
    ä¸ŃåĽ½åĮº
    -0.07
    åłķ
    -0.07
    æĪijåĽ½çļĦ
    -0.07
    åľ¨ä¸ŃåĽ½çļĦ
    -0.07
    å½¼
    -0.06
    POSITIVE LOGITS
    åħĪåIJİ
    0.09
    çİĩè¾¾
    0.09
    为éĩįçĤ¹
    0.09
    累计
    0.08
    ä¿IJ
    0.08
    åħĪå¾Į
    0.08
    æĪij们éĢļè¿ĩ
    0.08
    åģļåĪ°äºĨ
    0.08
    ä¸įéĹ´æĸŃ
    0.08
    ä¸įåIJĮç¨ĭ度
    0.08
    Activations Density 0.075%

    No Known Activations