© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62869
    Prev
    Next
    INDEX
    Explanations

    shapes and dimensions

    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
    涩
    -0.08
    çĭŀ
    -0.07
    大æłij
    -0.07
     Blond
    -0.07
    çĭĤ
    -0.07
    çĮ´åŃIJ
    -0.07
    onom
    -0.06
     level
    -0.06
    styr
    -0.06
    å±Ĥ
    -0.06
    POSITIVE LOGITS
    -shaped
    0.16
    å½¢çļĦ
    0.13
     shape
    0.12
    å½¢çĬ¶
    0.12
     اÙĦØ´ÙĥÙĦ
    0.11
     Ø´Ú©ÙĦ
    0.11
    çĬ¶çļĦ
    0.11
    å½¢
    0.11
    çĭĢ
    0.11
     모ìĸij
    0.11
    Activations Density 0.136%

    No Known Activations