© 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. 58767
    Prev
    Next
    INDEX
    Explanations

    introducing a statement or clarification

    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
    noop
    -0.08
    еÑģе
    -0.08
    errick
    -0.07
    ä¸Ńæĸĩç½ij
    -0.07
    erre
    -0.07
    pekt
    -0.07
    عÙĬÙĨ
    -0.07
    Tunes
    -0.07
    çº¿åĽ¾
    -0.07
    ÑĢеÑĨ
    -0.07
    POSITIVE LOGITS
    åĢ¼å¾Ĺä¸ĢæıIJçļĦæĺ¯
    0.10
     here
    0.08
    åĢ¼å¾Ĺä¸ĢæıIJ
    0.08
     briefly
    0.08
    说ä¸Ģä¸ĭ
    0.07
     ici
    0.07
    here
    0.07
    åĩłçĤ¹
    0.07
    åѦæ³ķ
    0.07
     noteworthy
    0.07
    Activations Density 0.362%

    No Known Activations