© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62938
    Prev
    Next
    INDEX
    Explanations

    Ray Lewis

    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
     Katz
    -0.07
    instein
    -0.07
    mtree
    -0.07
    .et
    -0.07
    -cols
    -0.07
    lau
    -0.07
    irable
    -0.07
     Goldberg
    -0.07
    æ
    -0.07
    rado
    -0.07
    POSITIVE LOGITS
    æĸ°å®ī
    0.06
    âĢij
    0.06
    ائÙĦ
    0.06
    aver
    0.06
    avy
    0.06
    äºĶæĺ¯
    0.06
     tens
    0.06
    娲
    0.06
     zem
    0.06
    é¢ĨèĪª
    0.06
    Activations Density 0.002%

    No Known Activations