© 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. 40550
    Prev
    Next
    INDEX
    Explanations

    actual, reality, for, case

    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
    æĭ¼
    -0.08
    éĥ½æ²¡
    -0.07
    ÄĽj
    -0.07
    reo
    -0.07
     виÑĤÑĢа
    -0.07
    åĴĮåİ¿
    -0.07
    ASIL
    -0.07
     ãĥIJãĥ¼
    -0.07
    klas
    -0.07
    antau
    -0.07
    POSITIVE LOGITS
     formal
    0.09
     actual
    0.09
    Actual
    0.08
    æŃ£å¼ıçļĦ
    0.08
    æŃ£å¼ı
    0.08
     specifics
    0.08
     formally
    0.08
    ä¹Łæĺ¯å¦ĤæѤ
    0.08
    åħ·ä½ĵæĿ¥è¯´
    0.07
     Formal
    0.07
    Activations Density 0.135%

    No Known Activations