© 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. 18522
    Prev
    Next
    INDEX
    Explanations

    to an

    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
    оÑĢÑĤи
    -0.09
    åĪ°åĵªéĩĮ
    -0.09
    ÙĪغ
    -0.08
    cxx
    -0.08
    .appspot
    -0.08
    vlo
    -0.08
    ysh
    -0.08
    acked
    -0.08
     Tribunale
    -0.08
    usti
    -0.08
    POSITIVE LOGITS
    æĸĩç«ł
    0.07
     r
    0.07
     question
    0.06
    人æĪĸ
    0.06
     article
    0.06
    ins
    0.06
    osis
    0.06
    æĺİçĻ½
    0.06
    çļĦè¦ģ
    0.06
    0.06
    Activations Density 0.068%

    No Known Activations