© 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. 44988
    Prev
    Next
    INDEX
    Explanations

    rounding numbers

    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
     Teixe
    -0.08
    åIJijæĹ¥
    -0.07
    zyman
    -0.07
    atson
    -0.07
    کر
    -0.07
    urunk
    -0.07
    scheid
    -0.07
    ÙĦÙĥ
    -0.07
    allen
    -0.07
    CES
    -0.07
    POSITIVE LOGITS
    æĢ§åľ°
    0.07
    è¯Ĩ
    0.07
    èŃĺ
    0.06
    æĸ¹èĪŁ
    0.06
    å²ij
    0.06
    èŀ
    0.06
    arily
    0.06
    æĢ§å¼º
    0.06
    eth
    0.06
    è¬Ģ
    0.06
    Activations Density 0.027%

    No Known Activations