© 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. 3225
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æľīæīį
    -0.08
    haf
    -0.07
    egr
    -0.07
    ekor
    -0.07
    aios
    -0.07
    εÏį
    -0.07
    å¸¸åľ¨
    -0.07
    ä¸ĢéĢļ
    -0.07
    ר×IJ
    -0.07
    ÑĦи
    -0.07
    POSITIVE LOGITS
    çĴ¨
    0.07
    é¹ıé£ŀ
    0.07
    itti
    0.07
    ernet
    0.07
    åIJĮä¸Ģ个
    0.06
    åıªè¦ģæĪij们
    0.06
    ilm
    0.06
    ä½ľä¸ºä¸Ģç§į
    0.06
    ztat
    0.06
    دت
    0.06
    Activations Density 0.000%

    No Known Activations