© 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. 44616
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    ä¹ĭæĺŁ
    -0.09
    ç§ĭ鼨
    -0.07
     instead
    -0.07
    arco
    -0.07
    ogne
    -0.07
    大åĪ©
    -0.07
    olio
    -0.06
    amani
    -0.06
    gne
    -0.06
     plutôt
    -0.06
    POSITIVE LOGITS
    ady
    0.08
    %E
    0.08
     daraus
    0.08
    indr
    0.07
    udz
    0.07
    æŃ£ç¡®ä½¿çĶ¨
    0.07
    èĩ³ä¸Ĭ
    0.07
    мÑĭÑħ
    0.07
    æŀĹåŃIJ
    0.07
    ngu
    0.07
    Activations Density 0.004%

    No Known Activations