© 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. 37896
    Prev
    Next
    INDEX
    Explanations

    UK, British, England

    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
    æĺŁè¾°
    -0.08
     Motel
    -0.08
    ullets
    -0.08
    Presidente
    -0.08
    ä¸ĩç¾İåħĥ
    -0.08
    秽
    -0.07
    plex
    -0.07
    chema
    -0.07
     Richter
    -0.07
    itemap
    -0.07
    POSITIVE LOGITS
    åľ¨èĭ±åĽ½
    0.16
    èĭ±åĽ½
    0.16
     England
    0.15
    èĭ±åĽ½çļĦ
    0.15
     British
    0.15
     Britain
    0.15
    èĭ±æł¼åħ°
    0.14
    British
    0.14
    èĭ±åľĭ
    0.13
    èĦ±æ¬§
    0.13
    Activations Density 1.514%

    No Known Activations