© 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. 3717
    Prev
    Next
    INDEX
    Explanations

    vacuum and empty space

    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
    å¾Ĺå¿ĥåºĶæīĭ
    -0.09
    å¤ĸæı´
    -0.09
    chai
    -0.09
    versed
    -0.08
    å¤ļåĸĿæ°´
    -0.08
    å°ijè§ģ
    -0.08
    OrFail
    -0.08
    èģĶè½´
    -0.08
    主æĶ»
    -0.08
    xeb
    -0.08
    POSITIVE LOGITS
    æģ¯
    0.08
     cosmic
    0.08
    ä¸įåģľçļĦ
    0.07
     Empty
    0.07
    空
    0.07
    .getDefault
    0.07
    èĻļæĹł
    0.07
     empty
    0.07
     vacuum
    0.06
    getDefault
    0.06
    Activations Density 0.005%

    No Known Activations