© 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. 3848
    Prev
    Next
    INDEX
    Explanations

    months, week, Temperature, airport

    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
    äºİ人
    -0.07
    inspace
    -0.07
    æ¯ıåĪ°
    -0.07
    memo
    -0.07
    inator
    -0.07
    каз
    -0.07
    aroo
    -0.07
    çļĦä¸ĸçķĮéĩĮ
    -0.07
    mus
    -0.07
    hey
    -0.07
    POSITIVE LOGITS
    abouts
    0.08
    åĴĮæĹ¥æľ¬
    0.07
     Utara
    0.07
    å¢ĥ
    0.07
    åĴĮåĽ½éĻħ
    0.07
    ensis
    0.06
    åIJĦæī§
    0.06
    .SuspendLayout
    0.06
    .locals
    0.06
     entière
    0.06
    Activations Density 0.120%

    No Known Activations