© 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. 21432
    Prev
    Next
    INDEX
    Explanations

    entities for physical objects or places

    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
    é¬ĵ
    -0.08
    éĹ¨å¤´
    -0.08
    å¥Īä½ķ
    -0.08
    ä¸įä»İ
    -0.08
    ä¸įæĶ¶
    -0.07
     TRAB
    -0.07
    å¹´å§ĭ
    -0.07
    æŁ»
    -0.07
     lás
    -0.07
    .shtml
    -0.07
    POSITIVE LOGITS
    frog
    0.07
    确认åIJİ
    0.07
    oton
    0.06
    yu
    0.06
    ycin
    0.06
     bref
    0.06
    ãģĦãģ£ãģŁ
    0.06
    lden
    0.06
    èĩ´
    0.06
    AMES
    0.06
    Activations Density 0.674%

    No Known Activations