© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14362
    Prev
    Next
    INDEX
    Explanations

    around, at, after, to

    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
    ä»»ä½ł
    -0.07
     [`
    -0.07
    å¦Ĥæĺ¯
    -0.07
    ä»»çĶ±
    -0.07
     ÏĥÏħνÎŃÏĩεια
    -0.06
    ovah
    -0.06
     *(*
    -0.06
    åľ¨è¿Ļç§į
    -0.06
    åºŀ大
    -0.06
    -describedby
    -0.06
    POSITIVE LOGITS
    Called
    0.09
    ä¸Ģå®ļçļĦ
    0.09
    æľĢ广
    0.08
    å¾Īå°ıçļĦ
    0.07
     Called
    0.07
    TM
    0.07
    Passed
    0.07
    _wr
    0.07
    å¾Īé«ĺçļĦ
    0.07
    olini
    0.07
    Activations Density 0.054%

    No Known Activations