© 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. 32616
    Prev
    Next
    INDEX
    Explanations

    mathematical and physics concepts

    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
     Jaya
    -0.07
    éªĭ
    -0.06
    affer
    -0.06
    erein
    -0.06
    ç·¨èĻŁ
    -0.06
     rats
    -0.06
    ennen
    -0.06
    ä¼ļåıĺæĪIJ
    -0.06
    å²±
    -0.06
    CERT
    -0.06
    POSITIVE LOGITS
    å®ļä¹ī为
    0.13
     defined
    0.11
    çļĦæ¦Ĥ念
    0.11
     Defined
    0.11
    Defined
    0.10
    æ¦Ĥ念
    0.10
    å®ļä¹ī
    0.10
    æ¦Ĥ念çļĦ
    0.10
     definition
    0.10
     Definition
    0.10
    Activations Density 0.047%

    No Known Activations