© 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. 27634
    Prev
    Next
    INDEX
    Explanations

    probability of picking k items

    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
     setting
    -0.07
    åŁİ乡
    -0.06
    jol
    -0.06
     subsidiary
    -0.06
    isz
    -0.06
    ãģ«åıĸãĤĬ
    -0.06
    3
    -0.06
    uto
    -0.06
    ÏĦαι
    -0.06
    ihal
    -0.05
    POSITIVE LOGITS
    çļĦè¿Ļç§į
    0.09
    ä¸İä¼Ĺä¸įåIJĮ
    0.08
    ãģ©ãģĵãĤį
    0.08
    ¯
    0.08
    ptom
    0.08
    +')
    0.08
    ittest
    0.08
    lei
    0.08
    çļĦéĥ½æĺ¯
    0.08
    اÙĩ
    0.07
    Activations Density 0.021%

    No Known Activations