© 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. 48446
    Prev
    Next
    INDEX
    Explanations

    infectious disease SIR models

    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
    çĸĻçĺ©
    -0.07
    æĮĽ
    -0.07
    ä»»æĢ§
    -0.06
    æŁij
    -0.06
    亲åİĨ
    -0.06
    åĬŁåĬĽ
    -0.06
     zig
    -0.06
     lit
    -0.06
    i
    -0.06
     tre
    -0.06
    POSITIVE LOGITS
    ç¹ģæ®ĸ
    0.12
    çī©ç§į
    0.09
    ingang
    0.09
     modele
    0.09
     toxin
    0.09
     modeled
    0.09
    멸
    0.09
    ÑĨен
    0.08
    çģŃ
    0.08
    ourn
    0.08
    Activations Density 0.012%

    No Known Activations