© 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. 34581
    Prev
    Next
    INDEX
    Explanations

    carousel and ui components

    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
    iep
    -0.07
    çݲçıij
    -0.07
     gas
    -0.07
    åħ¬
    -0.07
    åĩºäº§
    -0.07
    _byte
    -0.07
    è·¨
    -0.07
    溯æºIJ
    -0.07
    ../../../../
    -0.07
    æľĢæĸ°è¯Ħ论
    -0.07
    POSITIVE LOGITS
    _HORIZONTAL
    0.08
    allery
    0.07
    menti
    0.07
    人åİ»
    0.07
    vents
    0.07
    éĥ¸
    0.07
     controller
    0.07
    naan
    0.07
     controls
    0.07
    ×ķ×¢
    0.07
    Activations Density 0.322%

    No Known Activations