© 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. 55794
    Prev
    Next
    INDEX
    Explanations

    numbers, commas, dates, names

    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
    undi
    -0.07
    å½¢
    -0.06
    ubi
    -0.06
    ç²¾
    -0.06
    ÅĽl
    -0.06
    o
    -0.06
    usi
    -0.06
     Exercise
    -0.06
    æµij
    -0.06
    æĬ¥
    -0.06
    POSITIVE LOGITS
    æµ·æ¶Ľ
    0.08
    figcaption
    0.07
    ä¸įèĭŁ
    0.07
    orse
    0.07
    车åĨµ
    0.07
    ëĩ¨
    0.07
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.07
    _ty
    0.07
    inski
    0.07
    orsche
    0.07
    Activations Density 0.016%

    No Known Activations