© 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. 15808
    Prev
    Next
    INDEX
    Explanations

    season, cycle, week, intervals

    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
    åĬłåĭĴ
    -0.07
    æľµ
    -0.07
     serialized
    -0.07
    WA
    -0.07
    гло
    -0.07
     comp
    -0.07
    filesize
    -0.07
     serial
    -0.07
    )size
    -0.07
    ãĥŃãĥĥãĥĪ
    -0.06
    POSITIVE LOGITS
    湿
    0.07
     kateg
    0.07
    outu
    0.07
    ault
    0.07
    aux
    0.07
    ä¼ij
    0.07
     airs
    0.06
    çĻ»ä¸ĬäºĨ
    0.06
    å¥ĸæĥ©
    0.06
    éħ¸
    0.06
    Activations Density 0.293%

    No Known Activations