© 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. 11490
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or questions

    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
    ç½ij讯
    -0.08
    aum
    -0.08
    ngo
    -0.07
    èĻı
    -0.07
     Shall
    -0.07
    å£ģä¸Ĭ
    -0.07
    è®°èĢħä»İ
    -0.07
    _FS
    -0.07
    stra
    -0.07
    cej
    -0.07
    POSITIVE LOGITS
     ↵↵↵↵↵
    0.07
     ÙģÙĪت
    0.07
     ↵↵↵↵
    0.07
     ↵↵↵
    0.07
    antie
    0.07
     инг
    0.06
    طرة
    0.06
    (Int
    0.06
    ÙĦÙĥ
    0.06
    ↵↵↵
    0.06
    Activations Density 0.067%

    No Known Activations