© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30092
    Prev
    Next
    INDEX
    Explanations

    applying, apply

    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
    Ĺı
    -0.09
    anser
    -0.08
    ilier
    -0.08
    dorf
    -0.08
    зий
    -0.08
    ouvr
    -0.07
    ä½ķæŶ
    -0.07
    åij¼åĴĮ
    -0.07
     whence
    -0.07
    illis
    -0.07
    POSITIVE LOGITS
     principles
    0.10
     apply
    0.10
    apply
    0.09
     applies
    0.09
    è¿Ļç§įæĸ¹æ³ķ
    0.09
     applying
    0.09
    åºĶçĶ¨åĪ°
    0.09
     Apply
    0.09
    Apply
    0.09
    è¿Ļ个æĸ¹æ³ķ
    0.08
    Activations Density 0.050%

    No Known Activations