© 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. 2653
    Prev
    Next
    INDEX
    Explanations

    . it

    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
    otify
    -0.08
    ftime
    -0.07
    leys
    -0.07
    ief
    -0.07
    elier
    -0.07
    ley
    -0.07
    /il
    -0.07
    鸿
    -0.06
    ogue
    -0.06
    æ¯ıåĪĨéĴŁ
    -0.06
    POSITIVE LOGITS
    oons
    0.08
    ersi
    0.07
     terci
    0.07
    å§Ĺ
    0.07
    èĢĥçļĦ
    0.07
    ól
    0.07
    ربÛĮ
    0.07
    anter
    0.06
    _INCLUDED
    0.06
    icen
    0.06
    Activations Density 0.495%

    No Known Activations