© 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. 42101
    Prev
    Next
    INDEX
    Explanations

    numbers, slashes, and commas

    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
    èµĦ
    -0.08
    ç»ĵæĪIJ
    -0.07
    ONUS
    -0.07
    æīİå®ŀåģļ好
    -0.07
    bolt
    -0.07
    uke
    -0.07
    estina
    -0.07
     Hawks
    -0.06
     settling
    -0.06
    بÙĪÙĦ
    -0.06
    POSITIVE LOGITS
    omor
    0.06
    建å®ī
    0.06
    ãĤ
    0.06
    帼
    0.06
    à¹Ĭà¸Ķ
    0.06
    ä¼Ł
    0.06
    getOption
    0.06
     romant
    0.06
    renom
    0.06
    currentTime
    0.06
    Activations Density 0.057%

    No Known Activations