© 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. 62692
    Prev
    Next
    INDEX
    Explanations

    start [with/again/off/by/out/be]

    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
    ffit
    -0.09
    afa
    -0.07
     gevolg
    -0.07
    è¿ĺæľīä»Ģä¹Ī
    -0.07
    -ie
    -0.07
    ening
    -0.07
    (enable
    -0.07
    ide
    -0.07
    åĽłæĿIJæĸ½æķĻ
    -0.07
    ingatan
    -0.07
    POSITIVE LOGITS
     basics
    0.08
    æ¦Ĥè¿°
    0.06
    well
    0.06
    åIJ§
    0.06
    èij
    0.06
    è´¨çļĦ
    0.06
     Well
    0.06
    åħĪ
    0.06
    schw
    0.06
    izabeth
    0.06
    Activations Density 0.006%

    No Known Activations