© 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. 46328
    Prev
    Next
    INDEX
    Explanations

    asking "what do you mean" or "are you looking"

    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
    æľ¬ç«ĻåĨħ容
    -0.09
    ingue
    -0.09
    à¹ģม
    -0.09
    رت
    -0.08
    ugh
    -0.08
    nesia
    -0.07
    گرÛĮ
    -0.07
    queta
    -0.07
     Biography
    -0.07
    缸åħ³éĹ®çŃĶ
    -0.07
    POSITIVE LOGITS
    asan
    0.07
    æĺ¯æĮĩåľ¨
    0.07
    ons
    0.07
    æĮĩçļĦæĺ¯
    0.06
    çİ®
    0.06
    imple
    0.06
    ç¦
    0.06
    æĺ¯æĮĩ
    0.06
     vorba
    0.06
     chodzi
    0.06
    Activations Density 0.013%

    No Known Activations