© 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. 40157
    Prev
    Next
    INDEX
    Explanations

    reverse

    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
    _resolve
    -0.07
    åĪĨäºĨ
    -0.07
     ki
    -0.06
     odst
    -0.06
    èĦ±
    -0.06
    æĬĺ
    -0.06
    hini
    -0.06
    管
    -0.06
     contingency
    -0.06
    丰å¯Įå¤ļ彩
    -0.06
    POSITIVE LOGITS
    Reverse
    0.10
     reversing
    0.10
     reverse
    0.09
    .Reverse
    0.09
    reverse
    0.09
     Reverse
    0.09
    .reverse
    0.09
    åıįåIJij
    0.09
     reversed
    0.09
    _reverse
    0.09
    Activations Density 0.020%

    No Known Activations