© 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. 21226
    Prev
    Next
    INDEX
    Explanations

    calling or invoking

    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
     palm
    -0.07
     Palmer
    -0.07
    ç«ĻåĩºæĿ¥
    -0.06
    aglio
    -0.06
    èĩªå·±çĭ¬çī¹çļĦ
    -0.06
    æī¿è®¤
    -0.06
    åĩºäº§
    -0.06
    omitempty
    -0.06
    raft
    -0.06
    æĤ¨è¿ĺåı¯ä»¥
    -0.06
    POSITIVE LOGITS
    impa
    0.10
     calls
    0.09
    åij¼åı«
    0.09
     instantiate
    0.09
    è°ĥçĶ¨
    0.09
     invoked
    0.09
     invoke
    0.09
     call
    0.09
     instantiation
    0.09
     invoking
    0.09
    Activations Density 0.266%

    No Known Activations