© 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. 9123
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives: low, smaller, quite, significantly, fine, elevated, faster

    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
     sophistication
    -0.07
    ÑĩаÑı
    -0.07
    çĸij
    -0.07
    æľīåħ³çļĦ
    -0.07
    çļĦç¨ĭ度
    -0.07
     eleg
    -0.06
    builtin
    -0.06
    ylist
    -0.06
    ãĥ¼ãĤ·ãĥ§ãĥ³
    -0.06
     Weird
    -0.06
    POSITIVE LOGITS
     increased
    0.09
     high
    0.09
     reduced
    0.08
     ëĨĴìĿĢ
    0.08
     decreased
    0.08
     minimal
    0.08
    mlin
    0.08
    è¾ĥé«ĺçļĦ
    0.07
     strong
    0.07
     low
    0.07
    Activations Density 0.595%

    No Known Activations