© 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. 47838
    Prev
    Next
    INDEX
    Explanations

    lab experiment project report

    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
    TypeInfo
    -0.09
    åħ¥åѦèĢĥè¯ķ
    -0.08
    åĩºå¸Ńä¼ļè®®
    -0.08
    awat
    -0.08
    iliz
    -0.08
     ÙħÙĦÙģ
    -0.08
    ä¸ĵç§ijåĮ»éĻ¢
    -0.08
    opan
    -0.08
    ä¸ĵå®¶åĽ¢éĺŁ
    -0.08
    enek
    -0.08
    POSITIVE LOGITS
     experiment
    0.15
    å®ŀéªĮ
    0.14
    å®ŀéªĮä¸Ń
    0.13
    experiment
    0.12
     Experiment
    0.12
    Experiment
    0.11
    çļĦå®ŀéªĮ
    0.11
     experiments
    0.10
     expériment
    0.10
     experimental
    0.10
    Activations Density 0.041%

    No Known Activations