© 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. 63378
    Prev
    Next
    INDEX
    Explanations

    maximize function derivative calculus

    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
    ,:,:
    -0.07
    raid
    -0.07
     counted
    -0.07
    à²Ĥತ
    -0.07
     KIT
    -0.07
    ured
    -0.07
    undy
    -0.07
    åıªè¦ģæĺ¯
    -0.07
    äºĴéĢļ
    -0.07
    insen
    -0.07
    POSITIVE LOGITS
     maximize
    0.08
     derivative
    0.08
    æĹłæŀģ
    0.08
    åįķè°ĥ
    0.07
    /Peak
    0.07
    Peak
    0.07
    é©»
    0.07
     calculus
    0.07
    å³°
    0.07
    fcn
    0.07
    Activations Density 0.005%

    No Known Activations