© 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. 62349
    Prev
    Next
    INDEX
    Explanations

    tracking truck types

    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
    èĬĿåĬł
    -0.09
    å·¥ç¨ĭå¸ĪæĭĽèģĺ
    -0.08
    åĬłæĭ¿å¤§çļĦ
    -0.08
    çİĦå¹»éŃĶæ³ķ
    -0.08
    ../../../../
    -0.07
    å½ĵåºŃ
    -0.07
    æŃ¦ä¾łä¿®çľŁ
    -0.07
    éĺħè¯»æľ¬æĸĩåīį
    -0.07
    (Android
    -0.07
    WebKit
    -0.07
    POSITIVE LOGITS
     à®ħà®°à®ļ
    0.07
    å¾Ĺ天çĭ¬åİļçļĦ
    0.06
     обаÑĩ
    0.06
    顶å±Ĥ设计
    0.05
    åįĥ家ä¸ĩæĪ·
    0.05
    .guild
    0.05
     instansi
    0.05
    æĮĩ示精ç¥ŀ
    0.05
     "-//
    0.05
    .settings
    0.05
    Activations Density 37.117%

    No Known Activations