© 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. 31495
    Prev
    Next
    INDEX
    Explanations

    drilling, refrigerant, testing, web browser, page views, mousepad, lymph nodes, pixels, print driver

    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
    ially
    -0.08
    -thumbnails
    -0.07
    ##_
    -0.07
    edList
    -0.07
    ODO
    -0.06
    новен
    -0.06
    AndUpdate
    -0.06
     módon
    -0.06
    壳ä½ĵ
    -0.06
    ìĬµ
    -0.06
    POSITIVE LOGITS
    è¿Ļç§įä¸ľè¥¿
    0.08
    (?:
    0.07
    æĥĬå¿ĥåĬ¨
    0.07
    ×ŀר
    0.07
    veiller
    0.07
    å¡ļ
    0.07
    بÙĪÙĦ
    0.07
    ç¼ĶéĢł
    0.07
    èĦļè¸ıå®ŀ
    0.06
    .va
    0.06
    Activations Density 0.390%

    No Known Activations