© 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. 32776
    Prev
    Next
    INDEX
    Explanations

    PJ/B or PJtd

    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
     kepada
    -0.17
    åĪ°ä¸Ģ个
    -0.15
     to
    -0.15
    åĪ°å¤§
    -0.14
     Ø¥ÙĦÙĬÙĩ
    -0.14
     Ø¥ÙĦÙĬÙĩا
    -0.13
     Ø¥ÙĦÙī
    -0.13
    åĪ°ä»ĸ
    -0.13
    åĪ°çļĦ
    -0.12
    åĪ°äºº
    -0.12
    POSITIVE LOGITS
    好ç¬ij
    0.08
    å°ĨæĪij
    0.08
    ãĥ§ãĥ³
    0.07
    rake
    0.07
     khá»ıi
    0.07
     sullo
    0.07
    ikkel
    0.07
    ä¹ĿéľĦ
    0.07
    ForKey
    0.07
    apo
    0.07
    Activations Density 0.027%

    No Known Activations