© 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. 60810
    Prev
    Next
    INDEX
    Explanations

    Click HERE

    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
    eli
    -0.09
    ale
    -0.08
    enance
    -0.08
    ç½¢äºĨ
    -0.08
    èµ·æĿ¥åIJ§
    -0.08
    áĥĺáĥª
    -0.07
    sla
    -0.07
    ony
    -0.07
    åıªå¾Ĺ
    -0.07
    ÙĬØ©
    -0.07
    POSITIVE LOGITS
     Liber
    0.07
    ä¸įåĬ¨
    0.07
    ìłĢ
    0.06
    ä¸įæĿ¥
    0.06
    urch
    0.06
    amani
    0.06
    ä¸įåĭķ
    0.06
    è¿ĺè®°å¾Ĺ
    0.06
    aminer
    0.06
    å¾Ģå¾Ģæĺ¯
    0.06
    Activations Density 0.124%

    No Known Activations