© 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. 15578
    Prev
    Next
    INDEX
    Explanations

    local followed by noun

    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
    ÑĢик
    -0.08
    çļĦä¸ĸçķĮéĩĮ
    -0.08
    çݰ代社ä¼ļ
    -0.08
    aime
    -0.07
    hô
    -0.07
    ¢
    -0.07
    dap
    -0.07
    éria
    -0.07
     minist
    -0.07
    çݰ代人
    -0.07
    POSITIVE LOGITS
    /local
    0.15
    åıĬåij¨è¾¹
    0.11
    (local
    0.11
     setempat
    0.10
    æľ¬åľ°çļĦ
    0.10
    .local
    0.10
    /reg
    0.10
    .Local
    0.09
    (Local
    0.09
     local
    0.09
    Activations Density 0.098%

    No Known Activations