© 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. 65320
    Prev
    Next
    INDEX
    Explanations

    questions about technical subjects

    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¦ĤæѤçļĦ
    -0.09
    oter
    -0.08
    对äºİè¿ĻäºĽ
    -0.08
    æĪĸèĢħ缴æİ¥
    -0.07
    å¦ĤæѤ
    -0.06
    igor
    -0.06
    ain
    -0.06
    æĪĸæĺ¯
    -0.06
    å¦Ĥæŀľèĥ½å¤Ł
    -0.06
    åIJŀåIJIJ
    -0.06
    POSITIVE LOGITS
    lesa
    0.08
    Coder
    0.08
    è·¯ä¸İ
    0.08
    Ñijм
    0.07
    åħ¶äºĮ
    0.07
    mtx
    0.07
    ÑĩÑijÑĤ
    0.07
     vs
    0.07
    mgr
    0.07
    figcaption
    0.07
    Activations Density 0.145%

    No Known Activations