© 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. 1266
    Prev
    Next
    INDEX
    Explanations

    every or any

    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
    _using
    -0.08
    áni
    -0.08
    å¾ħå®ļ
    -0.08
    вÑĤÑĢа
    -0.07
    èijĨ
    -0.07
    èĦ±ç¦»äºĨ
    -0.07
    ##_
    -0.07
    éķij
    -0.07
    ζί
    -0.07
    imah
    -0.07
    POSITIVE LOGITS
    ä¸įä½İäºİ
    0.08
    ä»»ä½ķ
    0.07
    ä¸įå°ijäºİ
    0.07
     any
    0.07
    好æŃ¹
    0.07
    à¹Ģสมà¸Ń
    0.07
    èĩ³å°ij
    0.07
     every
    0.07
    ä¸įå°ıäºİ
    0.07
     either
    0.07
    Activations Density 0.017%

    No Known Activations