© 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. 41889
    Prev
    Next
    INDEX
    Explanations

    orientations, frequency, energy, positions

    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
    vÃŃ
    -0.08
    _WAKE
    -0.07
    anee
    -0.07
    åĬĽå£«
    -0.07
    æIJŃä¸Ĭ
    -0.07
    çķ´
    -0.07
    å¸Īå¾·
    -0.07
     напÑĢа
    -0.07
    æĸ°åĮº
    -0.07
    æĹ¥åĪ¶
    -0.07
    POSITIVE LOGITS
     complementary
    0.11
    plementary
    0.08
    ä¸įåIJĮè§Ĵ度
    0.08
     strategically
    0.08
    äºĴè¡¥
    0.08
    åģļå®ŀ
    0.07
     different
    0.07
    äºĴ为
    0.07
    å¤ļè§Ĵ度
    0.07
    urier
    0.07
    Activations Density 0.066%

    No Known Activations