© 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. 40673
    Prev
    Next
    INDEX
    Explanations

    place names ending in -boro, -burg, -hurst, -shire

    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
    åĴĮæĶ¿åºľ
    -0.06
    æ²¹çĽIJ
    -0.06
    è¿Ļç§įä¸ľè¥¿
    -0.06
    ikk
    -0.06
    çľģå§Ķ常å§Ķ
    -0.06
    linger
    -0.06
    çķĻåľ¨
    -0.06
    ä»ĸ乡
    -0.06
    æĪIJåijĺ
    -0.06
    å±ħä½ıåľ¨
    -0.06
    POSITIVE LOGITS
    çŃīåľ°çļĦ
    0.11
    Äįan
    0.10
    shire
    0.10
    å¸ĤçļĦ
    0.10
    åıĬåij¨è¾¹
    0.09
    sburg
    0.09
    hurst
    0.09
    ä¸Ģ带
    0.09
    éĻĦè¿ijçļĦ
    0.09
    -area
    0.09
    Activations Density 0.848%

    No Known Activations