© 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. 17100
    Prev
    Next
    INDEX
    Explanations

    immunomodulatory, power station, recording audio, medical care, science

    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
    .sy
    -0.08
    icamente
    -0.07
    ÙĦات
    -0.07
    otypical
    -0.07
    olut
    -0.07
     Sites
    -0.07
    ãĤĦãģĻ
    -0.07
    éħ¸çĶľ
    -0.07
    itters
    -0.07
    è¿ŀéĶģåºĹ
    -0.07
    POSITIVE LOGITS
    顺便
    0.11
    æįİ
    0.10
    éĻĦ带
    0.10
    为è¾ħ
    0.09
     incidental
    0.09
     broader
    0.09
    顺æīĭ
    0.09
    çļĦä¸ĢéĿ¢
    0.08
    ä¹Łæľīä¸Ģå®ļçļĦ
    0.08
    åħ·æľīä¸Ģå®ļçļĦ
    0.08
    Activations Density 0.578%

    No Known Activations