© 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. 13176
    Prev
    Next
    INDEX
    Explanations

    times between numbers

    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
    åįĥéĩij
    -0.08
    å°½æľī
    -0.08
    enschaft
    -0.07
    اسب
    -0.07
    .sourceforge
    -0.07
    为转载
    -0.07
    [++
    -0.07
    ARTH
    -0.07
    ocode
    -0.07
    ocene
    -0.07
    POSITIVE LOGITS
    å½ĵåľ°æŶéĹ´
    0.08
     midnight
    0.08
     noon
    0.07
    åĩĮæĻ¨
    0.07
     dawn
    0.07
    عاÙĦ
    0.07
     dusk
    0.06
      ↵↵
    0.06
    åºĻ
    0.06
    esting
    0.06
    Activations Density 0.356%

    No Known Activations