© 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. 46106
    Prev
    Next
    INDEX
    Explanations

    items in lists or data structures

    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
    isht
    -0.08
    è°·éĽ¨
    -0.08
    aised
    -0.08
    iglio
    -0.08
    ä¸Ģå¤ķ
    -0.07
    onsin
    -0.07
    getRepository
    -0.07
    mails
    -0.07
    _redirected
    -0.07
    Ñģловно
    -0.07
    POSITIVE LOGITS
    ç»ĵæĿŁåIJİ
    0.07
    å®ĮæĪIJåIJİ
    0.07
    å°ıé¢ĺ
    0.06
    å¸ĮæľĽä½łä»¬
    0.06
     unnamed
    0.06
    å®ĮåIJİ
    0.06
    æĥ³çľĭ
    0.06
     processed
    0.06
     delimited
    0.06
     XML
    0.06
    Activations Density 0.027%

    No Known Activations