© 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. 12676
    Prev
    Next
    INDEX
    Explanations

    math maxima and minima

    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
     presup
    -0.07
    ensi
    -0.07
    enius
    -0.07
    豪è¿Ī
    -0.07
    é»ĺ认
    -0.07
    èIJ½èĬ±
    -0.07
    osexual
    -0.06
    ches
    -0.06
    éĴ§
    -0.06
    perimental
    -0.06
    POSITIVE LOGITS
    èħĶ
    0.09
    å®ļæľŁçļĦãģ«
    0.08
     entire
    0.07
    rush
    0.07
     entirety
    0.07
    å¿Į
    0.07
    inian
    0.07
     Entire
    0.07
     periodically
    0.07
    azzi
    0.07
    Activations Density 0.005%

    No Known Activations