© 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. 34819
    Prev
    Next
    INDEX
    Explanations

    date and time calculations

    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
    acula
    -0.08
    åĢ¾åŁİ
    -0.07
    IFI
    -0.07
    æķĻ
    -0.07
    西æĸ¯
    -0.07
     Jord
    -0.07
     hữu
    -0.07
    izz
    -0.07
    zaak
    -0.06
    YL
    -0.06
    POSITIVE LOGITS
    ERRY
    0.07
    etan
    0.07
    éb
    0.07
    oline
    0.06
    erry
    0.06
     halfway
    0.06
     recal
    0.06
    å¾®è°ĥ
    0.06
     ìĽIJëŀĺ
    0.06
    æĺ¥èĬ±
    0.06
    Activations Density 0.010%

    No Known Activations