© 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. 51050
    Prev
    Next
    INDEX
    Explanations

    laptops, function, adventurers, disease, values

    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
     Pial
    -0.09
    ÙħاÙħ
    -0.08
    ianos
    -0.08
    åħ³æ³¨åħ¬ä¼Ĺåı·
    -0.08
    èĭ±æĸĩåIJįåŃĹ
    -0.08
    parg
    -0.08
    æī¿æĭħä¸ĢåĪĩ
    -0.08
    社åĨħ
    -0.08
    æī«æııä¸ĭæĸ¹äºĮç»´çłģ
    -0.07
    بÙĬØ©
    -0.07
    POSITIVE LOGITS
     Scr
    0.07
     scr
    0.06
    墨
    0.06
    am
    0.06
    ht
    0.06
    ä¸Ģ群人
    0.06
    eke
    0.05
    ä¸ĸ
    0.05
    æľĽ
    0.05
    cr
    0.05
    Activations Density 1.778%

    No Known Activations