© 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. 41794
    Prev
    Next
    INDEX
    Explanations

    copr, SL, orthogonal, gcd

    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
    追ä¸Ĭ
    -0.09
    رØŃ
    -0.08
    广大åħļåijĺ
    -0.08
    skon
    -0.08
    olas
    -0.07
    æĪĺæľ¯
    -0.07
    usione
    -0.07
    ä¹ĭæľĢ
    -0.07
    -arrow
    -0.07
    常åĬ¡ä¼ļè®®
    -0.07
    POSITIVE LOGITS
     status
    0.08
    status
    0.07
     gcd
    0.07
    WN
    0.07
    å¼ģ
    0.06
     indices
    0.06
    ä¸Ĭä»»
    0.06
    èĢĮä¸İ
    0.06
    æĭ¨
    0.06
     Status
    0.06
    Activations Density 0.002%

    No Known Activations