© 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. 40234
    Prev
    Next
    INDEX
    Explanations

    alpha cells, wheels, CBD, Picker, one

    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
    åĴĻ
    -0.07
    æĸ¹æ³ķçļĦ
    -0.07
    åĵĶ
    -0.07
    æ¯Ķè¾ĥ容æĺĵ
    -0.07
    _sources
    -0.07
    æĸ¹æ³ķ
    -0.07
    utherland
    -0.07
    åĴĮæĸ¹æ³ķ
    -0.07
    稿件æĿ¥æºIJ
    -0.06
    æĸ¹æ³ķæĺ¯
    -0.06
    POSITIVE LOGITS
    åIJĦåı¸
    0.09
    éĩįè¦ģä½ľçĶ¨
    0.07
    åıijæĮ¥ä½ľçĶ¨
    0.07
    波段
    0.07
    åħ¼åħ·
    0.07
    าà¸Ķ
    0.07
    ä¹IJä¸ļ
    0.07
    egt
    0.06
    ASK
    0.06
    irit
    0.06
    Activations Density 0.252%

    No Known Activations