© 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. 31713
    Prev
    Next
    INDEX
    Explanations

    closing brackets and parentheses

    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
    nite
    -0.08
    nyt
    -0.08
    bsolute
    -0.07
    缸è¾ħ缸æĪIJ
    -0.06
    insel
    -0.06
    jon
    -0.06
    allee
    -0.06
    .googleapis
    -0.06
    оÑĩно
    -0.06
    vain
    -0.06
    POSITIVE LOGITS
    ä¸ĭåIJĮ
    0.08
    ernels
    0.08
    ergestellt
    0.07
    为好åıĭ
    0.07
    agé
    0.07
    æĪijä¹Łåİ»
    0.07
    ifax
    0.07
    <|object_ref_end|>
    0.07
    ä¹ĭæīį
    0.07
     ...)
    0.07
    Activations Density 0.155%

    No Known Activations