© 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. 17051
    Prev
    Next
    INDEX
    Explanations

    (INT, Long, JSON, SOAP, As, X, Y, size)

    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¸ĢéĢļ
    -0.07
    æĭ¥
    -0.07
    èIJ±
    -0.07
    ĭ
    -0.07
    ÃŃz
    -0.06
    端
    -0.06
    รà¹Į
    -0.06
    Õ²
    -0.06
    zeb
    -0.06
    æľīåĬł
    -0.06
    POSITIVE LOGITS
    对åºĶçļĦ
    0.10
    æľĪåĴĮ
    0.08
     بÙĦÙĨد
    0.08
    sab
    0.07
    orsch
    0.07
    å®
    0.07
    æĹ¥åIJİçļĦ
    0.07
    转æį¢ä¸º
    0.07
    à§Į
    0.07
    çĽ¸å¯¹åºĶçļĦ
    0.07
    Activations Density 0.395%

    No Known Activations