© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46848
    Prev
    Next
    INDEX
    Explanations

    scintillations, phosphors, scintilligraphy

    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
    ../../../../
    -0.08
    ../../../
    -0.07
    blas
    -0.07
    å±¹
    -0.07
    pth
    -0.07
    ersh
    -0.07
    ewa
    -0.07
    ers
    -0.06
    anno
    -0.06
    篱
    -0.06
    POSITIVE LOGITS
    åħīæºIJ
    0.07
    ushing
    0.07
     Optical
    0.07
    andler
    0.07
    atos
    0.07
    åħ¬åı¸æĢ»ç»ıçIJĨ
    0.07
     autogenerated
    0.07
    ساط
    0.07
     vig
    0.07
     rod
    0.07
    Activations Density 0.005%

    No Known Activations