© 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. 23704
    Prev
    Next
    INDEX
    Explanations

    cleaning and cleanliness

    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
     doom
    -0.07
    稳å®ļ
    -0.07
     estabil
    -0.06
    æĹ©çĨŁ
    -0.06
    离åIJĪ
    -0.06
    æŃ¥åŃIJ
    -0.06
     unstable
    -0.06
    稳
    -0.06
    稳稳
    -0.06
     pacing
    -0.06
    POSITIVE LOGITS
    æ¸ħæ´ģ
    0.17
     cleaning
    0.15
     cleanliness
    0.14
    污åŀ¢
    0.14
     Cleaning
    0.14
    -clean
    0.13
    æ¸ħæ½Ķ
    0.13
    æ¸ħéĻ¤
    0.13
    _clean
    0.13
    Cleaning
    0.13
    Activations Density 0.125%

    No Known Activations