© 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. 28052
    Prev
    Next
    INDEX
    Explanations

    patient population, advisory roles, unknown reasons

    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
    åį¡åĴĮ
    -0.08
    æ²¹åĴĮ
    -0.08
    çī¹çĤ¹åĴĮ
    -0.08
    åħ¸
    -0.08
    æĶ¯æĮģåĴĮ
    -0.08
    åģ¥åº·åĴĮ
    -0.08
    çī¹çĤ¹çļĦ
    -0.07
     voici
    -0.07
    主é¢ĺçļĦ
    -0.07
    主è¦ģçļĦ
    -0.07
    POSITIVE LOGITS
    æķ°ä»¥
    0.08
    atters
    0.07
    dua
    0.07
    åĴĮæ°Ķ
    0.07
    让ä¸ĸçķĮ
    0.07
     Apro
    0.07
     dá»±ng
    0.07
    aggio
    0.06
    Recovered
    0.06
    æĺ¯æŶåĢĻ
    0.06
    Activations Density 1.269%

    No Known Activations