© 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. 27160
    Prev
    Next
    INDEX
    Explanations

    groups and organizations

    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
     giản
    -0.08
    æħĪ祥
    -0.07
    éĥ¨ä½įçļĦ
    -0.07
    款çļĦ
    -0.07
    istra
    -0.07
     gratuit
    -0.07
    atoren
    -0.07
    çŃīä¸Ģç³»åĪĹ
    -0.06
    ارÙĤ
    -0.06
    atest
    -0.06
    POSITIVE LOGITS
    æĪĸ个人
    0.13
    人马
    0.10
    ยà¹Īà¸Ńย
    0.10
    ä¹ĭä¸ĢçļĦ
    0.09
     halinde
    0.09
    zuge
    0.09
    æĪĸå¤ļ个
    0.08
    /groups
    0.08
    éĥ½æľīèĩªå·±çļĦ
    0.08
    åIJį称
    0.08
    Activations Density 0.221%

    No Known Activations