© 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. 38590
    Prev
    Next
    INDEX
    Explanations

    concludes that future

    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
    æ·±åıĹ广大
    -0.08
    Hint
    -0.08
    лÑĮÑģкого
    -0.08
     ÙĤب
    -0.08
    ebes
    -0.07
    è¾¾åĨħ
    -0.07
    lio
    -0.07
    度
    -0.07
    мееÑĤÑģÑı
    -0.07
    _internal
    -0.07
    POSITIVE LOGITS
    ĺ
    0.07
    ä¿®çļĦ
    0.07
     ë°ĶëŀĮ
    0.06
    èħĭä¸ĭ
    0.06
    为维æĬ¤
    0.06
     emphasizing
    0.06
    å¦Ĥéģĩ
    0.06
     emphas
    0.06
     concise
    0.06
    强è°ĥäºĨ
    0.06
    Activations Density 0.001%

    No Known Activations