© 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. 3463
    Prev
    Next
    INDEX
    Explanations

    dates and days of the week

    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
    è¡¥åħħ
    -0.07
    anya
    -0.07
    ovia
    -0.07
    绢
    -0.07
    çķ´
    -0.07
     supplementary
    -0.06
     Sent
    -0.06
    缴ç«ĭ
    -0.06
    ¹
    -0.06
    ä¾ĽåĽ¾
    -0.06
    POSITIVE LOGITS
    _cv
    0.08
    wap
    0.07
    otra
    0.07
    æīĢåľ¨ä½įç½®
    0.07
    hot
    0.07
    å®ļæľŁå¯¹
    0.07
     âĸ¼
    0.07
    ascus
    0.07
    禦
    0.07
    è¿ĩ客
    0.07
    Activations Density 0.973%

    No Known Activations