© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 59061
    Prev
    Next
    INDEX
    Explanations

    hardware, software, and computing systems

    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
    Negative Logits
    ÑģоÑĢ
    -0.09
    ions
    -0.09
    度é«ĺ
    -0.08
     
    -0.08
    mé
    -0.08
    obar
    -0.08
    é¡·
    -0.07
    eworthy
    -0.07
    tring
    -0.07
    ifestyles
    -0.07
    POSITIVE LOGITS
    /software
    0.12
     hardware
    0.07
    atical
    0.07
    .mozilla
    0.07
    atically
    0.07
    .parseInt
    0.06
    evers
    0.06
     Bakar
    0.06
    lacht
    0.06
    §
    0.06
    Activations Density 0.032%

    No Known Activations