© 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. 38496
    Prev
    Next
    INDEX
    Explanations

    "More" followed by links or transitions

    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
    ä»·æł¼æĮĩæķ°
    -0.07
    achten
    -0.07
    reiz
    -0.07
    avanaugh
    -0.07
     Rosario
    -0.07
    xdd
    -0.07
    xdf
    -0.06
    èݺ
    -0.06
    inson
    -0.06
    æģ¼
    -0.06
    POSITIVE LOGITS
     CASA
    0.07
    gai
    0.07
    åħį
    0.07
    ()._
    0.07
    âĢ¦the
    0.07
    ÙĬتÙĬÙĨ
    0.07
    thon
    0.07
     ÐŀÐĵ
    0.06
    ay
    0.06
    åįľ
    0.06
    Activations Density 0.414%

    No Known Activations