© 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. 31366
    Prev
    Next
    INDEX
    Explanations

    sum of, lacking, rich, son, onset

    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
    ebel
    -0.08
    çĻ»å½ķæŁ¥çľĭ
    -0.08
    åħ¨ç¤¾ä¼ļ
    -0.07
    å®ļå¾ĭ
    -0.07
    æŁ¥åĩº
    -0.07
    çİĭæµ·
    -0.07
    åıĮæĸ¹
    -0.07
    illions
    -0.07
    æĥħæĦı
    -0.07
     mdl
    -0.07
    POSITIVE LOGITS
    第ä¸Ģç§į
    0.09
    åĴĮä¸ĭ
    0.07
    第äºĮç§į
    0.07
    æľī两ç§į
    0.07
    åı¦ä¸Ģç§į
    0.06
    Ñĥз
    0.06
    æľī两个
    0.06
    atz
    0.06
    æ¸ħ宫
    0.06
    æľīå¤ļç§į
    0.06
    Activations Density 0.002%

    No Known Activations