© 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. 42114
    Prev
    Next
    INDEX
    Explanations

    reverse or mirror operation

    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
    uki
    -0.08
     Sond
    -0.07
    CONNECT
    -0.07
    çĭ
    -0.07
    ijt
    -0.07
    ento
    -0.07
    è·¯ç«Ļ
    -0.07
    è¿Ŀåıįä¸Ĭè¿°
    -0.06
    Upgrade
    -0.06
     Mayer
    -0.06
    POSITIVE LOGITS
    [::-
    0.15
     reversed
    0.12
    é¢łåĢĴ
    0.11
    (reverse
    0.11
     reversing
    0.11
    åıį转
    0.11
    .reverse
    0.10
    åºı
    0.10
     reversal
    0.10
    reverse
    0.10
    Activations Density 0.010%

    No Known Activations