© 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. 17068
    Prev
    Next
    INDEX
    Explanations

    mathematics and examples

    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
    ิà¹Īà¸Ļ
    -0.09
    ehme
    -0.08
    fried
    -0.08
    åıĬåħ¶åºĶçĶ¨
    -0.08
    Õ¹
    -0.08
    åĪ©åĻ¨
    -0.08
    为广大
    -0.08
    -dismiss
    -0.07
    .Suppress
    -0.07
     specialised
    -0.07
    POSITIVE LOGITS
    æĮīæ¯Ķä¾ĭ
    0.10
     math
    0.10
     logic
    0.10
     calculation
    0.10
     ratios
    0.09
    æݨç®Ĺ
    0.09
     proportions
    0.09
     scenario
    0.09
     proportion
    0.09
     calculate
    0.09
    Activations Density 0.109%

    No Known Activations