© 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. 9841
    Prev
    Next
    INDEX
    Explanations

    number theory context

    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
    ogie
    -0.07
    vena
    -0.07
    å°ı家
    -0.07
    åľ¨æĸ½å·¥
    -0.06
     Lees
    -0.06
    ör
    -0.06
    ä¾łå®¢
    -0.06
    lieÃŁ
    -0.06
    ä¸Ģåij³
    -0.06
    amol
    -0.06
    POSITIVE LOGITS
    onton
    0.07
    icz
    0.07
    æĤī
    0.07
    ç´°ç·»
    0.07
    .opens
    0.07
    .biz
    0.07
    æµı
    0.07
    isir
    0.07
     geile
    0.07
     astronom
    0.07
    Activations Density 0.001%

    No Known Activations