© 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. 9489
    Prev
    Next
    INDEX
    Explanations

    variable declaration or query

    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
    reja
    -0.07
    haj
    -0.07
    obet
    -0.07
    елÑı
    -0.07
    项
    -0.07
    饶
    -0.07
    yac
    -0.07
    cci
    -0.07
    neb
    -0.07
    ("."
    -0.07
    POSITIVE LOGITS
    绵
    0.08
    士æŀĹ
    0.08
    好
    0.07
    çĨ
    0.07
    _SER
    0.07
    æľ¬æĸĩæĿ¥èĩª
    0.07
    appa
    0.06
    æĤļ
    0.06
    æ£ī
    0.06
    isFunction
    0.06
    Activations Density 0.183%

    No Known Activations