© 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. 45607
    Prev
    Next
    INDEX
    Explanations

    math & code notation

    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
    å¾·æĸ¯
    -0.08
    ÙĩاÛĮÛĮ
    -0.07
    å±ł
    -0.07
     supers
    -0.07
    æīģ
    -0.07
    ee
    -0.06
    icos
    -0.06
    è¹Ń
    -0.06
    CH
    -0.06
    å®ĩ
    -0.06
    POSITIVE LOGITS
    éĩįéĩįçļĦ
    0.09
    untime
    0.07
    alley
    0.07
    ovn
    0.07
    èªĺ
    0.07
     Pilk
    0.07
    éĽĨåĽ¢æľīéĻIJ责任åħ¬åı¸
    0.07
    ÙĬدة
    0.07
    ëıĪ
    0.07
     reiv
    0.07
    Activations Density 0.001%

    No Known Activations