© 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. 24450
    Prev
    Next
    INDEX
    Explanations

    profile

    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
    ÙĬÙĩ
    -0.07
    å¡ģ
    -0.07
    ********************************************************************************
    -0.07
    ále
    -0.07
    ìŀIJ리
    -0.07
    é±¼
    -0.07
    @if
    -0.07
    orio
    -0.06
    .Fore
    -0.06
    uck
    -0.06
    POSITIVE LOGITS
    æľ¬æĸĩéĵ¾æİ¥
    0.07
    å®ļçļĦ
    0.07
    igen
    0.07
    家ä¼Ļ
    0.06
    ombat
    0.06
    ŀ
    0.06
    å½»
    0.06
    åĴ¬çīĻ
    0.06
     oblast
    0.06
    .compat
    0.06
    Activations Density 0.008%

    No Known Activations