© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 38426
    Prev
    Next
    INDEX
    Explanations

    lodash functions and documentation

    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
    è¶
    -0.07
    apult
    -0.07
    ÙĪع
    -0.07
    ÃŃnu
    -0.07
    udi
    -0.07
    ôt
    -0.07
    交代
    -0.06
     [&](
    -0.06
    رØŃ
    -0.06
    abyrinth
    -0.06
    POSITIVE LOGITS
    ijs
    0.08
    hil
    0.08
    åľı
    0.07
    æ´¼
    0.07
    kos
    0.07
    /assert
    0.07
     StringUtil
    0.07
     advoc
    0.07
    LEAN
    0.07
     overloaded
    0.07
    Activations Density 0.339%

    No Known Activations