© 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. 32651
    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
    han
    -0.07
    èŀį
    -0.07
    ly
    -0.06
     меÑĤаллиÑĩ
    -0.06
    ÙĪرÙĩا
    -0.06
    æĸ¹
    -0.06
    ä½ľä¸ļæŶ
    -0.06
    éĴ»
    -0.06
    åIJİçĶ¨
    -0.06
    å¾Ĵ
    -0.06
    POSITIVE LOGITS
    羣æŃ£æĦıä¹īä¸ĬçļĦ
    0.09
    IfNeeded
    0.08
    apol
    0.08
    æijĨåľ¨
    0.07
     dealloc
    0.07
    ÑĮÑĤеÑģÑĮ
    0.07
    çŃīé¢Ĩ导
    0.07
     поко
    0.07
    åĭĻ
    0.07
    æĺ¨å¤©æĻļä¸Ĭ
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.