© 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. 45665
    Prev
    Next
    INDEX
    Explanations

    variational and optimization problems

    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
    ymm
    -0.08
    زÙħ
    -0.08
    ÑĢÑĥз
    -0.08
    ege
    -0.08
    panse
    -0.07
    çľģå¤ĸ
    -0.07
    ÄŁer
    -0.07
    ewidth
    -0.07
    ç´¢æĢ§
    -0.07
     Barrel
    -0.07
    POSITIVE LOGITS
    åĩĨåĪĻ
    0.10
    çijķ
    0.07
     Wolfe
    0.07
    å¿ħè¦ģæĿ¡ä»¶
    0.07
    æĩĪ
    0.07
    è¾¹éĻħ
    0.07
    满足
    0.07
    æľīæĿ¡ä»¶
    0.07
    iff
    0.07
     governing
    0.07
    Activations Density 0.004%

    No Known Activations