© 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. 27331
    Prev
    Next
    INDEX
    Explanations

    generic type parameters `<T extends`

    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
    ķ
    -0.08
    —or
    -0.08
    umerator
    -0.07
    imah
    -0.07
    æĪĸèĢħ说
    -0.06
    izations
    -0.06
    çļĦçĶ·
    -0.06
    hani
    -0.06
    Ľ
    -0.06
    iali
    -0.06
    POSITIVE LOGITS
    stal
    0.08
    atra
    0.08
    {text
    0.07
    æĮļ
    0.07
    _decay
    0.07
    strup
    0.07
    缪
    0.06
    æľīæĿĥä¿ĿçķĻ
    0.06
    é¼
    0.06
    sstr
    0.06
    Activations Density 0.124%

    No Known Activations