© 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. 63074
    Prev
    Next
    INDEX
    Explanations

    Option, link, choice, said

    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
    çīĪæĿĥå½ĴåİŁä½ľèĢħ
    -0.08
    -utils
    -0.08
    aison
    -0.07
    бÑĢÑı
    -0.07
    ä»ĵ
    -0.07
    èĢ»
    -0.07
     Yat
    -0.07
    maÃŁ
    -0.07
    çģ¿
    -0.07
    æľīç§į
    -0.07
    POSITIVE LOGITS
    éĢī项ä¸Ń
    0.09
    éĢī项
    0.08
    anic
    0.08
    _DAC
    0.08
    èĢĥçĤ¹
    0.08
    éģ¸éłħ
    0.07
     Option
    0.07
    é¢ĺå¹²
    0.07
     option
    0.07
    à¸ķัวà¹Ģลืà¸Ńà¸ģ
    0.06
    Activations Density 0.013%

    No Known Activations