© 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. 13827
    Prev
    Next
    INDEX
    Explanations

    training, reduced, grazing, torrefied

    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
     Serv
    -0.07
    æĢİä¹ĪåĬŀåij¢
    -0.07
    Serv
    -0.06
    赤水
    -0.06
    OLA
    -0.06
    å¾Ĺä¸įåĪ°
    -0.06
    okka
    -0.06
    зиÑı
    -0.06
    å¾ij
    -0.06
    æĢ§æĪĸ
    -0.06
    POSITIVE LOGITS
     improves
    0.12
    æĶ¹åĸĦäºĨ
    0.11
     improve
    0.10
     compared
    0.10
     versus
    0.10
     Compared
    0.10
    æĶ¹åĸĦ
    0.09
    æıIJé«ĺäºĨ
    0.09
    æĺ¾èijĹæıIJåįĩ
    0.09
    缸æ¯Ķäºİ
    0.09
    Activations Density 0.237%

    No Known Activations