© 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. 9286
    Prev
    Next
    INDEX
    Explanations

    of an 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
    ioc
    -0.08
    rego
    -0.07
    оÑĩе
    -0.07
    aminer
    -0.07
    *scale
    -0.07
    ocie
    -0.07
    Scaled
    -0.07
    è°ĥçłĶåijĺ
    -0.07
    俱
    -0.06
    icolo
    -0.06
    POSITIVE LOGITS
    these
    0.07
    æŁIJ
    0.07
    ichte
    0.07
    è¿Ļç±»
    0.07
    让è¿ĻäºĽ
    0.07
    æ»ĭäºĭ
    0.07
    该类
    0.07
    ospel
    0.07
    _orientation
    0.07
    ield
    0.06
    Activations Density 1.335%

    No Known Activations