© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 54915
    Prev
    Next
    INDEX
    Explanations

    demonstrating, finding, assume, involves

    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
    Negative Logits
     mej
    -0.07
    cich
    -0.07
    没éĤ£ä¹Ī
    -0.07
    ertype
    -0.07
    èĤ©è´ŁçĿĢ
    -0.07
    รว
    -0.07
    ãģ¹
    -0.07
    ä¸įä¸Ģæł·
    -0.07
    uable
    -0.07
    èĤ©
    -0.06
    POSITIVE LOGITS
     involves
    0.08
     inherently
    0.08
     involve
    0.08
    verg
    0.07
     explicitly
    0.07
    æĹłä¸Ģ
    0.07
    æ¶īåıĬ
    0.07
    à°¨à±įà°¨
    0.07
     involving
    0.07
    onn
    0.07
    Activations Density 0.059%

    No Known Activations