© 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. 4238
    Prev
    Next
    INDEX
    Explanations

    symbol/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
    StyleSheet
    -0.07
    kunde
    -0.07
    loh
    -0.07
    ughs
    -0.07
    ativ
    -0.07
    èħ¥
    -0.07
    .datetime
    -0.07
    彩äºij
    -0.07
    ilde
    -0.07
     outright
    -0.07
    POSITIVE LOGITS
    象å¾ģçĿĢ
    0.15
    象å¾ģ
    0.14
     symbol
    0.14
    代表çĿĢ
    0.13
    代表äºĨ
    0.12
    Symbol
    0.11
     Symbol
    0.11
    ä½ĵçİ°äºĨ
    0.11
    symbol
    0.11
     simbol
    0.11
    Activations Density 0.057%

    No Known Activations