© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 28693
    Prev
    Next
    INDEX
    Explanations

    morse code

    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
    anut
    -0.08
    usable
    -0.07
    éĨī
    -0.07
    atan
    -0.07
    çIJ¼
    -0.06
    广
    -0.06
    缮ä¸Ń
    -0.06
    bacher
    -0.06
    ä¸į严
    -0.06
    æĺĨä»ij
    -0.06
    POSITIVE LOGITS
     combinations
    0.07
    uban
    0.07
    ael
    0.07
     encoding
    0.07
    æĺĤ
    0.07
    uracy
    0.07
    ipers
    0.07
    èħ
    0.07
    ħ
    0.07
    Ticks
    0.07
    Activations Density 0.005%

    No Known Activations