© 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. 22623
    Prev
    Next
    INDEX
    Explanations

    not followed by verb

    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
     unable
    -0.10
    ëģĶ
    -0.09
    avig
    -0.09
     incapable
    -0.08
     ÙĦÙĬست
    -0.08
    ä¿ĬæĿ°
    -0.08
    apun
    -0.08
    igraf
    -0.08
    ÑĥÑİÑī
    -0.08
    ifold
    -0.08
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.07
     há»ģ
    0.07
    åĽłä¸ºæĺ¯
    0.07
    æıIJä¾Ľä»»ä½ķ
    0.07
     have
    0.07
    æĿ¥å¾ĹåıĬ
    0.07
    è¿ĶåĽŀåĪĹ表
    0.06
    以任ä½ķ
    0.06
     yet
    0.06
     necessarily
    0.06
    Activations Density 0.191%

    No Known Activations