© 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. 8344
    Prev
    Next
    INDEX
    Explanations

    dark energy, fluids, matter, state

    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
     abbr
    -0.08
    幸è¿IJ
    -0.08
    åı·çłģ
    -0.08
    åıĬéĶĢåĶ®
    -0.08
    errupted
    -0.08
    ALLE
    -0.08
    ä¸Ģ度çļĦ
    -0.08
    بÙĪر
    -0.08
     Ero
    -0.08
    ç³»åĪĹ产åĵģ
    -0.08
    POSITIVE LOGITS
     density
    0.09
    å¯Ĩ度
    0.08
     densities
    0.08
     contributions
    0.07
     Density
    0.07
     gravitational
    0.07
    以太
    0.06
    å¼ķåĬĽ
    0.06
    åĪĨå¸ĥ
    0.06
    -density
    0.06
    Activations Density 0.002%

    No Known Activations