© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16884
    Prev
    Next
    INDEX
    Explanations

    unpredictable, variable, unique, irregular

    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
    æĮºçĽ´
    -0.08
    娴
    -0.08
    çī©çIJĨ
    -0.07
    æĹłå£°
    -0.07
     squarely
    -0.07
    ç¥ĸ
    -0.06
    彬彬
    -0.06
     stiff
    -0.06
    å®Į好
    -0.06
    aul
    -0.06
    POSITIVE LOGITS
     unpredictable
    0.21
     variability
    0.20
     unpredict
    0.19
    çģµæ´»
    0.18
    ä¸įå®ļ
    0.18
     flexible
    0.17
    å¤ļåıĺ
    0.17
    çģµæ´»æĢ§
    0.16
    çģµæ´»çļĦ
    0.16
    çļĦåĬ¨æĢģ
    0.16
    Activations Density 0.648%

    No Known Activations