© 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. 38970
    Prev
    Next
    INDEX
    Explanations

    occurred or occurs

    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
    bury
    -0.09
    /english
    -0.08
    ores
    -0.08
    oret
    -0.08
    ¹
    -0.08
    ¼
    -0.08
    ging
    -0.08
    lify
    -0.08
    iato
    -0.08
    ted
    -0.08
    POSITIVE LOGITS
    äºİä¸ĸ
    0.08
     bersamaan
    0.08
    incy
    0.08
    ãģ¾ãģĹãģ¦
    0.08
    Occurred
    0.08
    à¸Īริà¸ĩ
    0.08
    ä¸įåıijçĶŁ
    0.07
    ãĥ£
    0.07
    baugh
    0.07
    ncia
    0.07
    Activations Density 0.053%

    No Known Activations