© 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. 10913
    Prev
    Next
    INDEX
    Explanations

    torsion-free

    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
    andes
    -0.08
    xes
    -0.07
    åįĩåĪĿ
    -0.07
    çļĦåıĤæķ°
    -0.07
    olat
    -0.07
    å¤įæĿĤ度
    -0.07
    ãĥ³ãĤ¸
    -0.07
    鸣è¯Ń
    -0.07
    尼迪
    -0.07
    绾ç»İ
    -0.07
    POSITIVE LOGITS
    Tester
    0.07
    åĵģ缸
    0.07
     dru
    0.07
    å¼±
    0.07
     weaker
    0.07
    æľĢå¤ļçļĦ
    0.06
     Avery
    0.06
    åģ¥åħ¨
    0.06
    人åĥı
    0.06
     Tester
    0.06
    Activations Density 0.007%

    No Known Activations