© 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. 13037
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and numbers

    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
    itari
    -0.07
    裸
    -0.06
    oom
    -0.06
    رÙģت
    -0.06
    æİ©æĬ¤
    -0.06
     B
    -0.06
    ë¶Ī
    -0.06
    éĺŁåijĺ
    -0.06
    «
    -0.06
     True
    -0.06
    POSITIVE LOGITS
    æĿ¥ä¹ĭä¸įæĺĵ
    0.08
    icité
    0.08
     #__
    0.08
     dã
    0.07
    äg
    0.07
     Aloj
    0.07
    (#)
    0.07
    ICAS
    0.07
    ossible
    0.07
    TextUtils
    0.07
    Activations Density 0.011%

    No Known Activations