© 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. 8199
    Prev
    Next
    INDEX
    Explanations

    performance and efficiency improvements

    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
    dden
    -0.09
    ugin
    -0.09
    неж
    -0.08
    ä¸ĢåĪĩçļĦ
    -0.08
    çļĦä¸ĢåĪĩ
    -0.08
     Hogan
    -0.07
    第ä¸Ģæī¹
    -0.07
    太è¿ĩäºİ
    -0.07
    çīĪæĿĥå½ĴåİŁä½ľèĢħæīĢæľī
    -0.07
    ê´ĢìĹIJìĦľ
    -0.07
    POSITIVE LOGITS
    composite
    0.10
     collective
    0.10
     composite
    0.10
    å¤įåIJĪ
    0.09
    å¤įåIJĪåŀĭ
    0.09
    æĢ»æ¯Ķ
    0.08
     collectively
    0.08
    Composite
    0.08
    éĽĨä½ĵçļĦ
    0.08
    æĬ¬
    0.08
    Activations Density 0.084%

    No Known Activations