© 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. 64008
    Prev
    Next
    INDEX
    Explanations

    inverse and reciprocal operations

    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
    -indent
    -0.09
    æĥĬå¿ĥ
    -0.07
    urname
    -0.07
    æ¶Īè´¹éĩı
    -0.07
    æĭĦ
    -0.07
    еÑĢна
    -0.07
     Zel
    -0.07
    ×Ĺ×Ļ
    -0.07
    лаго
    -0.07
    izontal
    -0.07
    POSITIVE LOGITS
     reciprocal
    0.09
    _inverse
    0.09
     inverse
    0.09
     counterpart
    0.09
    Inverse
    0.08
     recip
    0.08
    inverse
    0.08
     invert
    0.08
    ^{-
    0.08
    代
    0.07
    Activations Density 0.009%

    No Known Activations