© 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. 45556
    Prev
    Next
    INDEX
    Explanations

    counting, mathematical expressions, programming constructs

    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
    ä»İéĩį
    -0.08
    çļĦéĩį
    -0.07
    ezza
    -0.07
    clar
    -0.07
    è¾ĥéĩį
    -0.07
    igel
    -0.07
    ohan
    -0.06
    vp
    -0.06
    zik
    -0.06
    ëģ¼
    -0.06
    POSITIVE LOGITS
     counts
    0.10
     count
    0.10
     counting
    0.09
    rowCount
    0.09
     تعداد
    0.09
    计æķ°
    0.09
    .count
    0.09
    -count
    0.09
     Count
    0.09
    .Count
    0.09
    Activations Density 0.011%

    No Known Activations