© 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. 23874
    Prev
    Next
    INDEX
    Explanations

    phases of processes or development

    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
    缴æİ¥ä»İ
    -0.07
    egin
    -0.07
    ä¸Ģ度çļĦ
    -0.06
    nü
    -0.06
    æĿ¥æŶ
    -0.06
    elat
    -0.06
    ä¸ĵä¸ļåĴĮ
    -0.06
    æĪĸåħ¶ä»ĸ
    -0.06
    emie
    -0.06
    zier
    -0.06
    POSITIVE LOGITS
    åĨįåĪ°
    0.10
    çŃīçݯèĬĤ
    0.09
     finally
    0.09
    缴èĩ³
    0.09
     thereafter
    0.09
     infine
    0.09
     enfin
    0.08
     schlieÃŁlich
    0.08
     anschlieÃŁ
    0.08
    çŃīä¸Ģç³»åĪĹ
    0.08
    Activations Density 0.171%

    No Known Activations