© 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. 43708
    Prev
    Next
    INDEX
    Explanations

    nested probabilities events partition

    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
    å·¡è§Ĩåijĺ
    -0.08
    æħ¢
    -0.07
     slower
    -0.07
    æŨ
    -0.07
    çĪ¬åĿ¡
    -0.07
    .RemoveAt
    -0.07
    ä¸įéĹ´æĸŃ
    -0.07
     slow
    -0.06
    asih
    -0.06
     Rosenstein
    -0.06
    POSITIVE LOGITS
    åĪĨåī²
    0.09
    éĿ¢ç§¯çļĦ
    0.08
    events
    0.08
    .Events
    0.08
    Nested
    0.08
    é¢ĸ
    0.07
    åĪĴåĪĨ
    0.07
     probabilities
    0.07
    tracts
    0.07
    nested
    0.07
    Activations Density 0.014%

    No Known Activations