© 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. 45731
    Prev
    Next
    INDEX
    Explanations

    mathematical delimiters and symbols

    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
    èĥ½å¤Łä¸º
    -0.08
    åŁºåľ°å»ºè®¾
    -0.08
    éĩĩ纳çİĩ
    -0.07
    åĪ°åºķæľīå¤ļ
    -0.07
    ãĥĹãĥĪ
    -0.07
    ä¹ĭ缮çļĦ
    -0.07
    .ua
    -0.07
    جاÙħ
    -0.07
    èĿ¶éĺĢ
    -0.07
    åī¯ä¸»ä»»
    -0.07
    POSITIVE LOGITS
    å·¥
    0.08
    ä¸ĢåįĬ
    0.07
    æ¦ľ
    0.07
    ently
    0.07
    à¸ĵี
    0.06
    ãģĹãĤĤ
    0.06
    çĩķ
    0.06
    é¥
    0.06
    梵
    0.06
    强
    0.06
    Activations Density 0.007%

    No Known Activations