© 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. 25615
    Prev
    Next
    INDEX
    Explanations

    variable names or code elements

    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
    æŃ»ä¸į
    -0.08
    æĬĬè¿ĻäºĽ
    -0.07
     Others
    -0.07
    ogi
    -0.07
    _tran
    -0.07
    åĤ³çµ±çļĦ
    -0.07
    aly
    -0.07
     centers
    -0.07
    æĬĬæīĢæľīçļĦ
    -0.07
    earn
    -0.07
    POSITIVE LOGITS
    æĪĸå°ij
    0.08
    èĻŀ
    0.08
    icz
    0.07
     Oder
    0.07
    åºĶäºĪ
    0.07
    éĥ¨éŨåĴĮ
    0.07
    æħ
    0.07
    éĥ½è§īå¾Ĺ
    0.06
    æĪĸåĪłéĻ¤
    0.06
    åIJ¾
    0.06
    Activations Density 0.146%

    No Known Activations