© 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. 34431
    Prev
    Next
    INDEX
    Explanations

    Q, R, or math expressions

    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
    à°³à±į
    -0.07
    omad
    -0.06
    ODY
    -0.06
    izzer
    -0.06
    ç´«èįĨ
    -0.06
    dav
    -0.06
    hci
    -0.06
    igon
    -0.06
    iskon
    -0.06
    ým
    -0.06
    POSITIVE LOGITS
    èĶĵ
    0.08
    Styled
    0.07
    æݨåĩº
    0.07
     incompatible
    0.07
    åħ¨æ¬¾
    0.07
    ç¼ĵç¼ĵçļĦ
    0.07
     ¬
    0.07
    ahari
    0.07
    æݨåĩºäºĨ
    0.07
    åĴ¸
    0.07
    Activations Density 0.001%

    No Known Activations