© 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. 24486
    Prev
    Next
    INDEX
    Explanations

    cryptographic operations and algorithms

    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
    autore
    -0.08
    ainter
    -0.08
    æ¸´æľĽ
    -0.07
    顺å¿ĥ
    -0.07
    åģıå¿ĥ
    -0.07
    Smarty
    -0.07
     Luxury
    -0.07
    isphere
    -0.07
    夹
    -0.07
    渴
    -0.07
    POSITIVE LOGITS
     cryptographic
    0.13
     cryptography
    0.10
     encryption
    0.09
    éĺ²èĮĥ
    0.09
     Attacks
    0.08
    对æĬĹ
    0.08
     plaintext
    0.08
    crypt
    0.08
     зло
    0.08
    æ¼ıæ´ŀ
    0.08
    Activations Density 0.108%

    No Known Activations