© 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. 12333
    Prev
    Next
    INDEX
    Explanations

    null hypothesis tests

    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
    iates
    -0.08
    aner
    -0.07
    umd
    -0.07
    жай
    -0.07
    åĽ¾æºIJ
    -0.07
     anale
    -0.07
    ragon
    -0.07
    ç¿Ķ
    -0.07
    hatian
    -0.07
    ాయ
    -0.07
    POSITIVE LOGITS
    bout
    0.08
     subset
    0.07
    æĪIJç«ĭ
    0.07
    æĪIJç«ĭçļĦ
    0.07
     hypotheses
    0.07
    åĿļå®ļåľ°
    0.07
    against
    0.07
     against
    0.07
    ä¸Ģåı£æ°Ķ
    0.06
    identification
    0.06
    Activations Density 0.005%

    No Known Activations