© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17592
    Prev
    Next
    INDEX
    Explanations

    uncertainties in data analysis

    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
    æº
    -0.08
    享
    -0.07
    èĮ
    -0.07
    Rh
    -0.07
     пÑĢикÑĢеп
    -0.07
     disrupt
    -0.07
     presenci
    -0.06
     quit
    -0.06
     dysfunctional
    -0.06
    é£İè¡Į
    -0.06
    POSITIVE LOGITS
     uncertainties
    0.10
    æī£éĻ¤
    0.09
     Monte
    0.09
     estim
    0.08
    æ¶ĪåĮĸçļĦ
    0.08
    æİ¢æµĭ
    0.08
     кали
    0.08
     Astroph
    0.08
    TeV
    0.07
    çĽ²
    0.07
    Activations Density 0.105%

    No Known Activations