© 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. 8115
    Prev
    Next
    INDEX
    Explanations

    of the

    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
    峡
    -0.08
    adoo
    -0.08
    å½¼æѤçļĦ
    -0.07
    人åijĺ对
    -0.07
    ä»·æł¼åIJĪçIJĨ
    -0.07
    athom
    -0.07
    çĶµè¯ĿèģĶç³»
    -0.07
    UAR
    -0.07
    iode
    -0.07
    imson
    -0.07
    POSITIVE LOGITS
     final
    0.09
     input
    0.08
    ÙĪÙĬد
    0.07
     ìµľì¢ħ
    0.07
    æľĢç»Ī
    0.07
    æī¿
    0.07
    ợ
    0.07
     target
    0.06
     incoming
    0.06
    kov
    0.06
    Activations Density 0.387%

    No Known Activations