© 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. 25601
    Prev
    Next
    INDEX
    Explanations

    names with 'a' or 'é'

    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
    reh
    -0.08
     verv
    -0.07
    UPI
    -0.07
    æĬĽå¼ĥ
    -0.07
    ewise
    -0.06
    rem
    -0.06
    个大
    -0.06
    ript
    -0.06
    é£ŁåĵģåĴĮ
    -0.06
    æĤīæķ°
    -0.06
    POSITIVE LOGITS
     pragma
    0.07
    éŁ³æłĩ
    0.07
     resp
    0.07
    åIJ¬éĹ»
    0.07
    åıijéŁ³
    0.07
    çŁ£
    0.07
    稳
    0.07
    Einst
    0.07
    akedown
    0.07
    åħįè´¹åıijå¸ĥ
    0.07
    Activations Density 0.015%

    No Known Activations