© 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. 56287
    Prev
    Next
    INDEX
    Explanations

    linear transformation, submodule, with common codomain

    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
    æ´²éĻħ
    -0.08
    kej
    -0.07
    äºĭäºĭ
    -0.07
    anje
    -0.07
    æīijéĿ¢èĢĮæĿ¥
    -0.07
    ä»»ä½ķä¸Ģç§į
    -0.07
    éģĩäºĭ
    -0.07
    橱çªĹ
    -0.07
    åĬłåĪ©
    -0.07
    éĩijä¸Ŀ
    -0.07
    POSITIVE LOGITS
    egel
    0.08
     inject
    0.08
    æĬµ
    0.07
    è·¯åĴĮ
    0.07
    æIJħ
    0.07
    å¾ĹåĬĽ
    0.07
    æĮĸ
    0.07
    asso
    0.07
    zinho
    0.07
    ÏĦÏģια
    0.07
    Activations Density 0.002%

    No Known Activations