© 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. 8263
    Prev
    Next
    INDEX
    Explanations

    points y and x

    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
    以ä¸Ĭ
    -0.07
    zen
    -0.07
    Run
    -0.06
     ÙĪØ¥ÙĦÙī
    -0.06
    ìĺģ
    -0.06
    j
    -0.06
     Bid
    -0.06
    лÑĥ
    -0.06
    run
    -0.06
    Äĩi
    -0.06
    POSITIVE LOGITS
    çĵ¦å°Ķ
    0.09
    efore
    0.08
    #ad
    0.08
    ideon
    0.08
    麾
    0.07
    icat
    0.07
    edata
    0.07
    -dat
    0.07
    æĹ¥ä¹ħ
    0.07
    _QU
    0.07
    Activations Density 0.003%

    No Known Activations