© 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. 34016
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

    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
    ĵĺ
    -0.07
    inkin
    -0.07
    èݹ
    -0.07
    eke
    -0.07
    ä½ľçĶ»
    -0.06
    天å¤ĸ
    -0.06
    ĺ
    -0.06
    åIJĥä¸ľè¥¿
    -0.06
    iget
    -0.06
    ÏĮ
    -0.06
    POSITIVE LOGITS
    龸çİĭ
    0.08
    ÙĦÙģت
    0.08
    alar
    0.07
    uin
    0.07
    æľ¬æł¼
    0.07
    ONUS
    0.07
    leven
    0.07
    engew
    0.07
    اÙĦÙĬØ©
    0.07
    lesh
    0.07
    Activations Density 0.010%

    No Known Activations