© 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. 48739
    Prev
    Next
    INDEX
    Explanations

    hotel, accommodations, lodging

    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
    治水
    -0.07
    æĵįåľºä¸Ĭ
    -0.07
    æŁĦ
    -0.07
    éĩį
    -0.06
    æĵįåľº
    -0.06
    èĩªçĦ¶çķĮ
    -0.06
    äºķçĽĸ
    -0.06
    aul
    -0.06
    ä½ľä¸ļ
    -0.06
    ÙĤاÙĦ
    -0.06
    POSITIVE LOGITS
     hotel
    0.13
    éħĴåºĹçļĦ
    0.12
    éħĴåºĹ
    0.11
    è¿ĩå¤ľ
    0.10
     hotels
    0.10
     accommodations
    0.10
     accommodation
    0.10
    éħĴåºĹ管çIJĨ
    0.10
     overnight
    0.10
    ë£
    0.10
    Activations Density 0.273%

    No Known Activations