© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48554
    Prev
    Next
    INDEX
    Explanations

    temperature and budget

    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
    eterminate
    -0.07
    åIJį家
    -0.07
    RowCount
    -0.07
    orz
    -0.06
    headed
    -0.06
    à¸Ĭัà¸Ļ
    -0.06
    ofd
    -0.06
     headaches
    -0.06
     trùng
    -0.06
     stutter
    -0.06
    POSITIVE LOGITS
    åĨ·æļĸ
    0.09
    赤éģĵ
    0.09
     cooling
    0.09
    æĶ¶æĶ¯
    0.08
     coolest
    0.08
    çļĦå¤ĸéĥ¨
    0.08
    æĻĴ太éĺ³
    0.08
    çĥŃéĩı
    0.08
    åĩī
    0.08
     ecu
    0.08
    Activations Density 0.003%

    No Known Activations