© 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. 16992
    Prev
    Next
    INDEX
    Explanations

    substitute for, replace with

    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
    åĮºåĪ«äºİ
    -0.08
    åѦåı²
    -0.08
    éĢļè¿ĩè¿Ļ个
    -0.08
    adu
    -0.07
    mare
    -0.07
    onav
    -0.07
    usst
    -0.07
    å¤ĸè§Ĥ设计
    -0.07
    edt
    -0.06
    è¿Ļ款软件
    -0.06
    POSITIVE LOGITS
    èĢĮ代ä¹ĭ
    0.15
     Ñģобой
    0.12
    æĽ¿
    0.12
    æĽ¿ä»£
    0.12
     replaced
    0.12
    åıĸèĢĮ代ä¹ĭ
    0.12
     substitute
    0.12
     replacement
    0.11
     replaces
    0.11
     replace
    0.11
    Activations Density 0.127%

    No Known Activations