© 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. 28702
    Prev
    Next
    INDEX
    Explanations

    exposure limits

    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
    éĥ½æľīåħ¶
    -0.07
    æĸ¹å¼ı使çĶ¨
    -0.07
    obre
    -0.07
    جا
    -0.07
    çĴŀ
    -0.07
    ä¸Ķåħ·æľī
    -0.07
    velt
    -0.06
    باÙĩ
    -0.06
    inux
    -0.06
     Ones
    -0.06
    POSITIVE LOGITS
    çļĦæ¦Ĥ念
    0.10
    å®ļä¹ī为
    0.09
    æ¦Ĥ念
    0.08
    ç¡®å®ļ为
    0.07
    åįģ足
    0.07
    ILING
    0.07
    akai
    0.07
    èIJ¨å°Ķ
    0.07
    æ¦Ĥ念çļĦ
    0.07
    agaan
    0.07
    Activations Density 0.022%

    No Known Activations