© 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. 31555
    Prev
    Next
    INDEX
    Explanations

    pairs, matched, symmetry

    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
     fraction
    -0.07
    ock
    -0.06
    ole
    -0.06
    éĤ£åıª
    -0.06
     fraud
    -0.06
     Sta
    -0.06
     strain
    -0.06
    籤
    -0.06
    åħ¨æĸ°çļĦ
    -0.06
    éĤ£å¼ł
    -0.06
    POSITIVE LOGITS
    对称
    0.18
     symmetric
    0.16
     Sym
    0.15
     symmetry
    0.15
     sym
    0.14
    _sym
    0.14
    sym
    0.14
    ä¸į对称
    0.14
    Sym
    0.14
    éħį对
    0.13
    Activations Density 0.013%

    No Known Activations