© 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. 13847
    Prev
    Next
    INDEX
    Explanations

    cancel/cancellation/order issues

    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
     sna
    -0.08
    оÑī
    -0.07
    æ¨Ĭ
    -0.07
    atted
    -0.07
    alisi
    -0.07
    enburg
    -0.07
    æijĺæĬĦ
    -0.06
    aid
    -0.06
     copied
    -0.06
     separat
    -0.06
    POSITIVE LOGITS
    åįĬéĢĶ
    0.13
    åIJİæĤĶ
    0.12
    æĴ¤åĽŀ
    0.12
    ä¸ŃéĢĶ
    0.12
    cancel
    0.12
     cancelling
    0.12
     cancellation
    0.12
    -cancel
    0.12
     reconsider
    0.12
     aborted
    0.12
    Activations Density 0.277%

    No Known Activations