© 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. 56699
    Prev
    Next
    INDEX
    Explanations

    first occurrence or initial

    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
    pron
    -0.07
    ulti
    -0.07
    çİīå±±
    -0.06
     maintained
    -0.06
    æľĢåIJİ
    -0.06
     pron
    -0.06
    fade
    -0.06
    æĿŃ
    -0.06
     last
    -0.06
    æĽ²æ±Ł
    -0.06
    POSITIVE LOGITS
     inaugural
    0.11
    第ä¸Ģ个
    0.10
    第ä¸Ģæī¹
    0.10
    é¦ĸ次
    0.09
    Initializer
    0.09
     Ø£ÙĪÙĦÙī
    0.09
    第ä¸Ģ项
    0.09
     Initial
    0.09
     initial
    0.09
     erste
    0.09
    Activations Density 0.027%

    No Known Activations