© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11766
    Prev
    Next
    INDEX
    Explanations

    reference spectrum

    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
    cac
    -0.08
    æ»ĭ
    -0.07
    -inc
    -0.07
    Õ©
    -0.07
    qli
    -0.06
    гни
    -0.06
    oust
    -0.06
    (logging
    -0.06
    ä¸įè¿ĩåľ¨
    -0.06
    inx
    -0.06
    POSITIVE LOGITS
    .define
    0.07
    ãģĤãģ®
    0.07
    .findBy
    0.07
    åIJĮ类产åĵģ
    0.07
    ãĤĥ
    0.07
    è¿ijåľ¨
    0.07
    åľ¨æĹģè¾¹
    0.07
    对èĩªå·±çļĦ
    0.06
    alez
    0.06
    .findOne
    0.06
    Activations Density 0.014%

    No Known Activations