© 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. 56793
    Prev
    Next
    INDEX
    Explanations

    optical information recording

    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
     kém
    -0.07
    åĬłåħ¥æĶ¶èĹı
    -0.07
    èµ·çļĦ
    -0.07
    个åŃIJ
    -0.07
     Gr
    -0.06
    èµ·äºĨ
    -0.06
    лÑİ
    -0.06
     gr
    -0.06
    康åģ¥
    -0.06
    æĪĺ
    -0.06
    POSITIVE LOGITS
    acin
    0.08
    ampa
    0.08
    ajem
    0.07
    obet
    0.07
    arius
    0.07
    hydr
    0.07
    arios
    0.07
    otti
    0.06
     rus
    0.06
    acent
    0.06
    Activations Density 0.051%

    No Known Activations