© 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. 24962
    Prev
    Next
    INDEX
    Explanations

    originally, historically, operationally

    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
    evere
    -0.08
     anyways
    -0.08
     Finally
    -0.07
    æľĢåIJİ
    -0.07
    –and
    -0.07
     Lastly
    -0.07
    æľĢåIJİæĺ¯
    -0.07
    æľĢåIJİåľ¨
    -0.07
          ↵↵
    -0.06
    æĪijè¿ĺè¦ģ
    -0.06
    POSITIVE LOGITS
    æľī以ä¸ĭ
    0.08
    Globals
    0.07
    æł¹æį®åħ¶
    0.07
    以ä¸ĭæĸ¹å¼ı
    0.07
    {%
    0.07
    åħ·æľī以ä¸ĭ
    0.07
    ä½Ĩä¸İ
    0.07
    ç¬
    0.07
    ä¸İæĮijæĪĺ
    0.07
    æľīä¸ĭåĪĹ
    0.06
    Activations Density 0.083%

    No Known Activations