© 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. 31077
    Prev
    Next
    INDEX
    Explanations

    mathematical notation

    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
    天ä¸ĬçļĦ
    -0.07
    дÑı
    -0.06
    ainer
    -0.06
    åĮ®
    -0.06
    åĽŃåĮº
    -0.06
    EME
    -0.06
    forth
    -0.06
     поÑĢоÑĪок
    -0.06
    _customize
    -0.06
    kins
    -0.05
    POSITIVE LOGITS
    人ä¸į
    0.09
    //=
    0.08
    ussy
    0.08
    ÐłÐIJÐĴ
    0.08
    åĩºä¹İ
    0.07
    满足äºİ
    0.07
    åīªåĪĢ
    0.07
    dbl
    0.07
    çݯå¢ĥä¼ĺç¾İ
    0.07
    åĬĩåł´
    0.07
    Activations Density 0.016%

    No Known Activations