© 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. 38270
    Prev
    Next
    INDEX
    Explanations

    Department

    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
    ØŃÙĬ
    -0.08
    å½ĵ羣
    -0.07
    бие
    -0.07
    ÑĭÑĢ
    -0.07
    åĽŀå¡«
    -0.07
    дзе
    -0.07
    burgh
    -0.07
     //[
    -0.07
     Obr
    -0.06
    trup
    -0.06
    POSITIVE LOGITS
    mlin
    0.08
    à¹Į
    0.07
    ape
    0.07
    wal
    0.07
    æī±
    0.07
    rees
    0.07
    ostream
    0.06
    ores
    0.06
    erra
    0.06
    arde
    0.06
    Activations Density 0.001%

    No Known Activations