© 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. 20100
    Prev
    Next
    INDEX
    Explanations

    any travel occasion

    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
    为ä»Ģä¹Īåij¢
    -0.09
     wichtigsten
    -0.08
    jenigen
    -0.08
    led
    -0.08
    à§Ģয়
    -0.08
    .nz
    -0.08
    uess
    -0.08
     Entire
    -0.08
    ÙĨز
    -0.08
     belangrijkste
    -0.08
    POSITIVE LOGITS
    THING
    0.12
    /all
    0.11
    æĥħåĨµä¸ĭ
    0.10
    where
    0.09
     conceivable
    0.08
    æĶ¾çŁ¢
    0.08
    اÙĭ
    0.08
    бÑĥдÑĮ
    0.08
    maal
    0.08
    mals
    0.08
    Activations Density 0.111%

    No Known Activations