© 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. 18954
    Prev
    Next
    INDEX
    Explanations

    decrypt, decode, encrypt

    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
    .escape
    -0.08
    è®©æĽ´å¤ļ人
    -0.08
    eliz
    -0.08
    让å°ı
    -0.08
    inspace
    -0.07
    è®©æĽ´å¤ļ
    -0.07
    产éĶĢ
    -0.07
     kerül
    -0.07
    表达èĥ½åĬĽ
    -0.07
    prus
    -0.07
    POSITIVE LOGITS
     decrypt
    0.11
    è¿ĺåİŁ
    0.11
    æĶ¶åĪ°
    0.11
     reconstruct
    0.10
    解å¯Ĩ
    0.10
     decryption
    0.10
     correct
    0.10
     correctly
    0.10
     reconstruction
    0.10
    æİ¥æĶ¶
    0.10
    Activations Density 0.169%

    No Known Activations