© 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. 65183
    Prev
    Next
    INDEX
    Explanations

    percentages and amounts

    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
    odyn
    -0.07
    itsu
    -0.07
     descriptions
    -0.07
    -hook
    -0.07
    ovel
    -0.06
    andu
    -0.06
    und
    -0.06
    æıIJé«ĺèĩªèº«
    -0.06
     NEC
    -0.06
     description
    -0.06
    POSITIVE LOGITS
    Margins
    0.08
    Margin
    0.08
    margin
    0.08
    TextWriter
    0.08
    kau
    0.07
    .margin
    0.07
    .Center
    0.07
     margins
    0.07
    -margin
    0.07
     زÙĬÙĨ
    0.07
    Activations Density 0.002%

    No Known Activations