© 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. 42381
    Prev
    Next
    INDEX
    Explanations

    disjoint cycle decomposition

    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
    Inc
    -0.07
    çļĵ
    -0.07
    çĿ¦
    -0.07
    ä¸ĢéŨ
    -0.07
     unarmed
    -0.07
     litt
    -0.07
     inc
    -0.06
    ä¸Ģ举
    -0.06
    åľ°åĪ©
    -0.06
    岩
    -0.06
    POSITIVE LOGITS
     portions
    0.08
    azzi
    0.08
    ìĺ¥
    0.08
     repetitions
    0.08
    azan
    0.08
    ÑĢио
    0.08
    ected
    0.07
     Tobias
    0.07
     decomposition
    0.07
    AZE
    0.07
    Activations Density 0.023%

    No Known Activations