© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 37558
    Prev
    Next
    INDEX
    Explanations

    code decoding or encryption

    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
    Negative Logits
     watchers
    -0.07
     Mert
    -0.07
     EITHER
    -0.07
    è¡¡éĩı
    -0.06
    éĢ®
    -0.06
     gifs
    -0.06
    åı£å¤´
    -0.06
     compt
    -0.06
    į
    -0.06
    Thrown
    -0.06
    POSITIVE LOGITS
     decoded
    0.10
     decrypted
    0.10
    解çłģ
    0.10
     decipher
    0.09
     encoded
    0.09
    decoded
    0.09
     clue
    0.09
     encrypted
    0.09
     Decode
    0.09
    è¿ĺåİŁ
    0.09
    Activations Density 0.057%

    No Known Activations