© 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. 43828
    Prev
    Next
    INDEX
    Explanations

    questions with star

    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
    tof
    -0.07
    å¯Ĵæ°Ķ
    -0.07
    åľ°åŁŁ
    -0.06
     pan
    -0.06
    croft
    -0.06
     Nase
    -0.06
    ìĬ¹
    -0.06
    çijķ
    -0.06
     chrom
    -0.06
     mon
    -0.06
    POSITIVE LOGITS
     freshman
    0.08
    à¸Ńั
    0.08
     Burger
    0.08
    uyer
    0.08
     freshmen
    0.08
    樣
    0.07
     midterm
    0.07
    ourg
    0.07
    Ø®ÛĮ
    0.07
    .note
    0.07
    Activations Density 0.021%

    No Known Activations