© 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. 3933
    Prev
    Next
    INDEX
    Explanations

    the equals sign in mathematical expressions and variable assignments.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jrosseruk
    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
    azza
    -0.09
    ones
    -0.08
    .....
    -0.08
    éĵ®
    -0.08
    нем
    -0.07
    çļĦå½¢å¼ı
    -0.07
    å³¥
    -0.07
    èķ
    -0.07
    ese
    -0.07
     hopefully
    -0.07
    POSITIVE LOGITS
     upward
    0.08
     “
    0.08
    ubile
    0.08
    ä¹ĭ忧
    0.07
    bsites
    0.07
    á»Ļng
    0.07
    porate
    0.07
    0.07
    oretical
    0.07
    Tmp
    0.07
    Activations Density 0.000%

    No Known Activations