© 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. 18679
    Prev
    Next
    INDEX
    Explanations

    therefore, accordingly, reason

    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
     meanwhile
    -0.08
    ä¸įå°±æĺ¯
    -0.08
    åį³åı¯å®ĮæĪIJ
    -0.08
    èİ«éĿŀ
    -0.08
    åıĪä¸įæĺ¯
    -0.07
    iagnostics
    -0.07
     ternyata
    -0.07
    æĹłéĿŀ
    -0.07
    loor
    -0.07
     btw
    -0.07
    POSITIVE LOGITS
     often
    0.10
    ìĿ¸ì§Ģ
    0.09
    æľīæŶ
    0.09
    æł¼å¤ĸ
    0.08
     неÑĢедко
    0.08
    æĺ¾å¾Ĺæł¼å¤ĸ
    0.08
    often
    0.08
    ä¹Łå°±ä¸į
    0.08
     sometimes
    0.08
    æīįæľīäºĨ
    0.08
    Activations Density 0.326%

    No Known Activations