© 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. 61271
    Prev
    Next
    INDEX
    Explanations

    mathematical inequalities and sets

    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
    opt
    -0.07
     opt
    -0.07
    为çĪ±
    -0.06
     Opt
    -0.06
    udar
    -0.06
     each
    -0.06
    æ¯ı
    -0.06
    λιÏĥ
    -0.06
     optical
    -0.06
    çĶŁè®¡
    -0.06
    POSITIVE LOGITS
    ä»ĭäºİ
    0.09
    大äºİ
    0.08
    Ranges
    0.08
    ä»ĭ
    0.08
    itra
    0.08
    éĴĿ
    0.08
     Raya
    0.08
     ultrap
    0.08
    ä¸ĭéĻIJ
    0.08
    -transitional
    0.08
    Activations Density 0.004%

    No Known Activations