© 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. 50354
    Prev
    Next
    INDEX
    Explanations

    Chinese characters or hanzi

    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
    ÑģкÑĥ
    -0.07
    isson
    -0.07
    directories
    -0.07
    >Note
    -0.07
    ãĥŁãĥ¼
    -0.07
     Cari
    -0.07
    andi
    -0.07
    人éĢł
    -0.07
    olvers
    -0.07
    intl
    -0.06
    POSITIVE LOGITS
    å¸
    0.08
    à¥įह
    0.07
    æ½Ł
    0.07
    ëŀ
    0.06
    ecto
    0.06
    çĶ»
    0.06
    å¦ĤæŀľæĤ¨å¯¹
    0.06
    ìĺ¥
    0.06
    tait
    0.06
    eries
    0.06
    Activations Density 0.034%

    No Known Activations