© 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. 16736
    Prev
    Next
    INDEX
    Explanations

    numbers and ordinals

    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
    -0.09
    Ø©
    -0.08
    女æĢ§æľĭåıĭ
    -0.08
    ï¸ı
    -0.07
    meister
    -0.07
    szy
    -0.07
    esch
    -0.07
    ãĤ£
    -0.07
    esc
    -0.07
    lash
    -0.07
    POSITIVE LOGITS
    ftware
    0.07
    é©Ł
    0.07
    çŁŃæļĤ
    0.07
    人æ°ijæĶ¿åºľ
    0.07
    åħ¶ä»ĸ
    0.07
    段çļĦ
    0.07
    elik
    0.06
     broader
    0.06
    第ä¸ī款
    0.06
    صرÙĬ
    0.06
    Activations Density 0.006%

    No Known Activations