© 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. 17474
    Prev
    Next
    INDEX
    Explanations

    matrix delimiters and operations

    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
    ÃŁe
    -0.07
    çªĿ
    -0.07
    åIJİ宫
    -0.07
    chos
    -0.07
    áŀ¶áŀĢáŁĭ
    -0.06
    اذ
    -0.06
     Rh
    -0.06
    gew
    -0.06
    cpy
    -0.06
    ä¹ħèĢĮ
    -0.06
    POSITIVE LOGITS
    ×ĵת
    0.08
    ä¸įå¾Ĺ以任ä½ķ
    0.07
    _DIRECTION
    0.07
    anz
    0.07
    leaflet
    0.07
    å°ıåĪ°
    0.07
    aries
    0.07
    alf
    0.07
    ×ĵ×ķת
    0.07
    çĴĢ
    0.07
    Activations Density 0.012%

    No Known Activations