© 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. 51445
    Prev
    Next
    INDEX
    Explanations

    negative numbers and subtraction

    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
    ç§ĭæ°´
    -0.08
    à®Łà¯ģதà¯įத
    -0.08
    æģ¶
    -0.08
    以æѤ
    -0.08
    æ²³æµģåŁŁ
    -0.08
    ç»Ĩå¿ĥçļĦ
    -0.08
    订éĺħä¸ĵæłı
    -0.08
    adop
    -0.07
    ezo
    -0.07
    ucid
    -0.07
    POSITIVE LOGITS
    oud
    0.06
    ume
    0.06
    ordi
    0.06
    Ú©ÛĮ
    0.06
    UniqueId
    0.06
    èªįå®ļ
    0.06
    upa
    0.06
     Ekon
    0.06
    ily
    0.05
    éĥ¨ä»½
    0.05
    Activations Density 0.114%

    No Known Activations