© 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. 46713
    Prev
    Next
    INDEX
    Explanations

    thousands of professional

    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
    oš
    -0.08
    à¸ĩ
    -0.07
    彤
    -0.07
    è¿ŀåIJĮ
    -0.07
    è¾°
    -0.07
    ç«ĭ交桥
    -0.07
    berger
    -0.07
     Bethlehem
    -0.07
    鬼
    -0.07
    हन
    -0.07
    POSITIVE LOGITS
     sond
    0.07
    oppel
    0.07
    quilla
    0.07
    yla
    0.06
    裾
    0.06
    éĢŁ
    0.06
    ersi
    0.06
    eros
    0.06
    gt
    0.06
    ressing
    0.06
    Activations Density 0.004%

    No Known Activations