© 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. 30319
    Prev
    Next
    INDEX
    Explanations

    anagrams, acronyms, puns

    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
    æĺİç¡®è§Ħå®ļ
    -0.08
     Stout
    -0.08
    åįĥç¯ĩ
    -0.07
    æĺŁæłĩ
    -0.07
    åĴĮæľĢ
    -0.07
    æľ½
    -0.07
    纫
    -0.07
    注æĺİ
    -0.07
    |h
    -0.07
    azer
    -0.07
    POSITIVE LOGITS
    è°IJéŁ³
    0.10
     conson
    0.09
    å·§åIJĪ
    0.08
    西æŀĹ
    0.08
    æĹłæĦıä¸Ń
    0.07
     spelling
    0.07
    çݩ转
    0.07
     concaten
    0.07
    æĭ¼
    0.07
     phon
    0.07
    Activations Density 0.032%

    No Known Activations