© 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. 1576
    Prev
    Next
    INDEX
    Explanations

    symbol or symbolic meaning

    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
    è¿Ļæīįæĺ¯
    -0.07
    æľīåij³
    -0.07
    å®ŀéĻħä¸Ĭ
    -0.07
    å°±æĺ¯æĪij
    -0.06
    acom
    -0.06
     titular
    -0.06
    æııè¿°äºĨ
    -0.06
    æĺİçıł
    -0.06
     actually
    -0.06
    -described
    -0.06
    POSITIVE LOGITS
     symbolism
    0.16
     symbol
    0.16
    象å¾ģ
    0.15
    象å¾ģçĿĢ
    0.14
    symbol
    0.14
     symbolic
    0.14
     Ñģимволи
    0.13
    Symbol
    0.13
     Ñģимвол
    0.13
    çļĦ象å¾ģ
    0.13
    Activations Density 0.054%

    No Known Activations