© 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. 38272
    Prev
    Next
    INDEX
    Explanations

    Nyhavn 11, alignment, ’s Bird, Primary diffuse, Marriott Vacation, IV variants, Nexus, 2020, Two big

    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
    ilton
    -0.06
    ciÄħ
    -0.06
    à¸ķà¹Īาà¸ĩ
    -0.06
    åıĪæĥ³
    -0.06
    гли
    -0.06
    Ħ
    -0.06
     dec
    -0.06
     st
    -0.06
    äºķåĨĪ
    -0.06
    ÑģÑĤви
    -0.06
    POSITIVE LOGITS
    Õ¼
    0.09
    Öģ
    0.08
     ës
    0.08
    ãģ«éĻIJ
    0.08
     totiž
    0.08
    æĮĩçļĦæĺ¯
    0.08
    ä»»ä½ķåħ¶ä»ĸ
    0.08
    </think>
    0.08
     infatti
    0.08
    .:**
    0.07
    Activations Density 0.125%

    No Known Activations