© 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. 60954
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and solutions

    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
    cid
    -0.07
    INGER
    -0.07
    _keyword
    -0.07
    ABCDEFG
    -0.07
    _decor
    -0.07
    ä¸İ人
    -0.07
    å°Ķå¤ļ
    -0.07
    ndice
    -0.06
    erto
    -0.06
    æ´Ĵ
    -0.06
    POSITIVE LOGITS
    æį¢åı¥è¯Ŀ说
    0.08
    åį³
    0.07
    aten
    0.07
    åį³åľ¨
    0.07
    úz
    0.07
     eli
    0.07
    ides
    0.07
    har
    0.06
    è°ĥåĴĮ
    0.06
    eis
    0.06
    Activations Density 0.003%

    No Known Activations