© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 8836
    Prev
    Next
    INDEX
    Explanations

    year or date

    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
     Trinh
    -0.08
    klä
    -0.08
    缴æİ¥æĪĸéĹ´æİ¥
    -0.08
    .toFloat
    -0.07
    åĪ°æŶ
    -0.07
    .Ui
    -0.07
    haal
    -0.07
    IZACIÃĵN
    -0.07
    ĥĿ
    -0.07
    ãĤ¹ãĥ³
    -0.07
    POSITIVE LOGITS
     revised
    0.09
    éĩįæĸ°
    0.08
     updated
    0.08
    çīĪæľ¬
    0.08
    修订
    0.08
    æĶ¹çīĪ
    0.08
     version
    0.08
     revision
    0.07
    并äºİ
    0.07
     modified
    0.07
    Activations Density 0.271%

    No Known Activations