© 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. 33049
    Prev
    Next
    INDEX
    Explanations

    counting microbial colonies and cultures

    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
    COPE
    -0.08
    estream
    -0.07
     renegot
    -0.07
    天çĶŁçļĦ
    -0.06
    è¾ĵçĶµ
    -0.06
    渡ãģĹ
    -0.06
     turbulent
    -0.06
    IKE
    -0.06
    çļĦåĨħ
    -0.06
    åħ¶åIJį
    -0.06
    POSITIVE LOGITS
     incub
    0.10
     colonies
    0.09
    æİ¥ç§į
    0.09
    åŁ¹åħ»
    0.09
    æĹłèıĮ
    0.09
    åŁ¹åħ»åĩº
    0.09
     isol
    0.08
    agar
    0.08
     viable
    0.08
     viability
    0.08
    Activations Density 0.038%

    No Known Activations