© 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. 39686
    Prev
    Next
    INDEX
    Explanations

    carcinoid, osteosarcoma, Fest, triglycerides, neonicotinoid, basement membrane cells

    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
    oop
    -0.07
    auta
    -0.07
    ảo
    -0.07
    uce
    -0.07
    izr
    -0.07
    æ¿
    -0.06
    踩çĿĢ
    -0.06
    åĬ³
    -0.06
    ij
    -0.06
    å¼±
    -0.06
    POSITIVE LOGITS
    æĹłè®ºæĺ¯åľ¨
    0.13
     wherever
    0.13
    æĹłå¤Ħä¸įåľ¨
    0.13
    贯穿äºİ
    0.11
    Anywhere
    0.11
     Everywhere
    0.11
     everywhere
    0.11
     везде
    0.11
    éļıå¤Ħåı¯è§ģ
    0.10
    æĹłè®ºåľ¨
    0.10
    Activations Density 0.516%

    No Known Activations