© 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. 38571
    Prev
    Next
    INDEX
    Explanations

    specifies how you want

    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
     cheap
    -0.09
    æīĢè°ĵ
    -0.09
     stuff
    -0.08
    æīĭæľºå®¢æĪ·ç«¯
    -0.08
    cheap
    -0.08
    æīĢè¬Ĥ
    -0.08
     supposed
    -0.08
    Cheap
    -0.07
    âĿ¤ï¸ı
    -0.07
     somehow
    -0.07
    POSITIVE LOGITS
    æľīä¸ĭåĪĹ
    0.08
    详æĥħ请
    0.08
    æľī以ä¸ĭ
    0.07
    åħ·æľī以ä¸ĭ
    0.07
    ä¸ĭåĪĹ
    0.07
     subparagraph
    0.07
    æľ¬èĬĤ
    0.07
    .localized
    0.07
    ä¸ĭ表
    0.07
    rieg
    0.07
    Activations Density 0.250%

    No Known Activations