© 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. 48197
    Prev
    Next
    INDEX
    Explanations

    accented characters and special glyphs

    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
    ÑģÑı
    -0.12
    al
    -0.10
    اÙĨ
    -0.10
    an
    -0.08
    se
    -0.08
    able
    -0.08
    ×ķ
    -0.08
    ÛĮ
    -0.08
    en
    -0.08
    Ùĩ
    -0.07
    POSITIVE LOGITS
    ¥
    0.11
    à¯įத
    0.11
    ÑĥÑģÑĤа
    0.10
    waran
    0.10
    ailles
    0.10
    ìį¨
    0.10
    aille
    0.09
    ª
    0.09
    onnier
    0.09
    ê¹IJ
    0.09
    Activations Density 0.008%

    No Known Activations