© 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. 56445
    Prev
    Next
    INDEX
    Explanations

    encoding, ciphers, and codes

    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
    descr
    -0.08
    olith
    -0.08
    à¸ŀà¸Ļ
    -0.08
    vas
    -0.08
    çijľ
    -0.07
     disag
    -0.07
    ç»´
    -0.07
    容
    -0.07
    ,array
    -0.07
    为转载
    -0.07
    POSITIVE LOGITS
     letters
    0.08
     encrypt
    0.08
     letter
    0.08
    åŃĹæ¯į
    0.08
     conson
    0.08
     alph
    0.08
     correspondence
    0.07
    -letter
    0.07
    letter
    0.07
     alphabet
    0.07
    Activations Density 0.023%

    No Known Activations