© 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. 21146
    Prev
    Next
    INDEX
    Explanations

    alphabetical sorting

    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
    eaux
    -0.08
    å¥Īä½ķ
    -0.07
    hle
    -0.07
    åĴĮä¸į足
    -0.07
    amoto
    -0.07
    以ä¸Ĭå°±æĺ¯å°ıç¼ĸ
    -0.07
    иÑĤелÑĮÑģÑĤво
    -0.07
    물ìĿĦ
    -0.07
    enschaften
    -0.07
    以ä¸Ĭå°±æĺ¯åħ³äºİ
    -0.07
    POSITIVE LOGITS
    ize
    0.09
    ically
    0.08
    licable
    0.07
    onso
    0.07
    lett
    0.07
    itr
    0.07
    iah
    0.07
    azard
    0.07
    lic
    0.07
    头æĿ¡
    0.07
    Activations Density 0.004%

    No Known Activations