© 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. 2391
    Prev
    Next
    INDEX
    Explanations

    theory and practice

    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
     revan
    -0.09
    Õ»
    -0.08
    ùm
    -0.08
    uhr
    -0.08
    tuj
    -0.08
    жай
    -0.08
     séc
    -0.07
    EventManager
    -0.07
    stel
    -0.07
    ä½łä¸įæĺ¯
    -0.07
    POSITIVE LOGITS
     theoretical
    0.16
    çIJĨ论
    0.13
     theor
    0.13
    çļĦçIJĨ论
    0.13
     theory
    0.13
     theorists
    0.13
     abstract
    0.12
    çIJĨè®ºçŁ¥è¯Ĩ
    0.12
    oretical
    0.12
    æĬ½è±¡
    0.12
    Activations Density 0.044%

    No Known Activations