© 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. 43486
    Prev
    Next
    INDEX
    Explanations

    find numerical expressions

    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
    ahi
    -0.08
    äst
    -0.07
    oir
    -0.07
    æĶ¹
    -0.07
    apixel
    -0.07
     McGregor
    -0.07
    éĿĴèī²
    -0.07
     McKenzie
    -0.07
     shit
    -0.07
     Weiner
    -0.07
    POSITIVE LOGITS
    æĿ¥æİ¥
    0.08
    åĸĦ
    0.07
    wald
    0.07
    odz
    0.07
    SHA
    0.07
    éģįéĩİ
    0.07
    jev
    0.06
    äºĨä¸ĢæĬĬ
    0.06
    éĢ¢
    0.06
    ached
    0.06
    Activations Density 0.452%

    No Known Activations