© 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. 56225
    Prev
    Next
    INDEX
    Explanations

    inequalities and loops

    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¦ıç¦Ħ
    -0.08
    éĢĤé¾Ħ
    -0.07
    åħ¶ä¸ī
    -0.07
    æ·¹
    -0.07
     alternatively
    -0.07
    alj
    -0.07
    ijen
    -0.07
    èİĺ
    -0.07
    sdale
    -0.07
     Act
    -0.07
    POSITIVE LOGITS
    iquer
    0.08
    çļĦä¸ĭ
    0.07
    isper
    0.07
    åİ®
    0.07
    erk
    0.07
    çļĦæľĢå°ı
    0.07
    Distinct
    0.07
    åĴĮä¸ĭ
    0.07
    otas
    0.07
     distinct
    0.07
    Activations Density 0.001%

    No Known Activations