© 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. 51676
    Prev
    Next
    INDEX
    Explanations

    political figures names

    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
    ASM
    -0.07
    é½IJ
    -0.07
    ajes
    -0.07
    ught
    -0.07
    ãģ¨ãģĦãģĨãĤĤãģ®
    -0.06
    è§Ĥ
    -0.06
    次æĹ¥
    -0.06
    اخت
    -0.06
    èĤĨ
    -0.06
     gespannt
    -0.06
    POSITIVE LOGITS
    为主导
    0.10
    ä¸»å¯¼åľ°ä½į
    0.10
    主导
    0.09
     dominance
    0.09
    æĪIJ为
    0.09
    åħ·å¤ĩäºĨ
    0.09
    èĥ½æĪIJ为
    0.09
     dominating
    0.08
     supremacy
    0.08
     dominate
    0.08
    Activations Density 0.319%

    No Known Activations