© 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. 32262
    Prev
    Next
    INDEX
    Explanations

    relational calculus queries

    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
     abs
    -0.06
    çķ¥æĺ¾
    -0.06
    å¼ĢæºIJ
    -0.06
    轻巧
    -0.06
    ä¸ĢçĤ¹ä¸Ģæ»´
    -0.06
    sey
    -0.06
    æŃ£ä¸Ń
    -0.06
     relative
    -0.06
    icot
    -0.06
    æľīçĤ¹
    -0.06
    POSITIVE LOGITS
    åħ¶éģĵ
    0.11
    åħ¶åIJį
    0.11
    å½ĵåħ¶
    0.09
     OTHERWISE
    0.09
    ä¸įå¾ĹäºĨ
    0.08
    janya
    0.08
    åħ¶èĩªçĦ¶
    0.08
    otka
    0.08
     desar
    0.08
    _typeof
    0.08
    Activations Density 0.131%

    No Known Activations