© 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. 3090
    Prev
    Next
    INDEX
    Explanations

    quenching/damping

    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
    asikan
    -0.07
    uint
    -0.07
    à¹ĩà¸ļ
    -0.07
    inales
    -0.07
    zinho
    -0.07
    ially
    -0.07
    arre
    -0.07
    -serving
    -0.06
    aciones
    -0.06
    éĻ¢æł¡çļĦ
    -0.06
    POSITIVE LOGITS
    æİīçļĦ
    0.12
    åīĤ
    0.10
    äºĨäºĭ
    0.10
    æİī
    0.09
    ä¸įä½ıçļĦ
    0.08
    æİīäºĨ
    0.08
    ers
    0.08
    ä¸įäºĨçļĦ
    0.08
    çģŃ
    0.08
    สà¸Ļิà¸Ĺ
    0.08
    Activations Density 0.010%

    No Known Activations