© 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. 32537
    Prev
    Next
    INDEX
    Explanations

    United Kingdom, U.S. Pat

    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
    ä¸ĢæĿ¥
    -0.08
    åħīæĺ¯
    -0.07
    íĻĶëĬĶ
    -0.07
    æĽ´è½»æĿ¾
    -0.06
    æĬĬèĩªå·±
    -0.06
    人åİ»
    -0.06
     sanz
    -0.06
    ï¸ı
    -0.06
    ernity
    -0.06
    çĶ¨å®ĥ
    -0.06
    POSITIVE LOGITS
    åºĦéķĩ
    0.08
    èĭ±æĸĩåIJįåŃĹ
    0.07
    izzo
    0.07
    áŀ½
    0.07
     denominada
    0.07
     aforementioned
    0.07
    agan
    0.07
    éĢĤå½ĵåľ°
    0.07
    ä¸įä¹ħçļĦ
    0.07
    à»Ī
    0.07
    Activations Density 1.741%

    No Known Activations