© 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. 20479
    Prev
    Next
    INDEX
    Explanations

    levels and scales

    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
    rowave
    -0.09
    ä¹ĭ主
    -0.08
    rias
    -0.08
    ipay
    -0.08
    ugas
    -0.08
     incond
    -0.08
    amis
    -0.08
    æł·åŃIJ
    -0.08
    idor
    -0.07
    bish
    -0.07
    POSITIVE LOGITS
    å±ĤéĿ¢
    0.15
     level
    0.15
    level
    0.14
    å±Ĥ次
    0.14
    -level
    0.14
    å±ĤéĿ¢çļĦ
    0.13
    å±Ĥ次çļĦ
    0.13
    å±ĤéĿ¢ä¸Ĭ
    0.13
    å±Ĥ级
    0.13
    Level
    0.13
    Activations Density 0.147%

    No Known Activations