© 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. 3685
    Prev
    Next
    INDEX
    Explanations

    names after "town"

    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
    å¦Ĥåħ¶
    -0.07
    åĪĽå»ºäºİ
    -0.07
    å¼Ģå±ķç»ıèIJ¥æ´»åĬ¨
    -0.07
    çĨŁçļĦ
    -0.07
    eric
    -0.07
    éĢĤ
    -0.07
    éģ©
    -0.07
    ä¸įå¾Ĺ以任ä½ķ
    -0.07
    atories
    -0.07
    ä¹ĭæĺŁ
    -0.07
    POSITIVE LOGITS
     Comics
    0.07
    åįĹå±±
    0.07
    è¶ĭ
    0.06
    æıIJéĨĴ
    0.06
    PyObject
    0.06
    èµ¢å¾Ĺ
    0.06
    ika
    0.06
     Salvatore
    0.06
    eted
    0.06
    åĮĹ
    0.06
    Activations Density 0.105%

    No Known Activations