© 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. 27399
    Prev
    Next
    INDEX
    Explanations

    quantum cryptography and protocols

    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
    anser
    -0.08
    angsa
    -0.08
    halat
    -0.08
    گرد
    -0.08
    azah
    -0.08
    ë¹ĦìĬ¤
    -0.07
     команди
    -0.07
    ÑĢенÑĮ
    -0.07
    lando
    -0.07
    PARSE
    -0.07
    POSITIVE LOGITS
     protocols
    0.09
     protocol
    0.09
    éĩıåŃIJ
    0.08
    ä¸Ń继
    0.08
    ä¼łè¾ĵ
    0.08
     quantum
    0.08
     Quantum
    0.08
     Protocol
    0.07
     photon
    0.07
     photons
    0.07
    Activations Density 0.018%

    No Known Activations