© 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. 25728
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and expressions

    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
    vét
    -0.09
    æľĿ天
    -0.08
    memcmp
    -0.08
     vặt
    -0.08
    strncmp
    -0.07
    zust
    -0.07
    жем
    -0.07
    å¤ļäºİ
    -0.07
    ndon
    -0.07
    essem
    -0.07
    POSITIVE LOGITS
    æľīéģĵ
    0.08
    å°ģ
    0.08
     added
    0.08
     addition
    0.07
     factor
    0.07
    èIJĥ
    0.07
    factor
    0.06
     afterwards
    0.06
     Factor
    0.06
     Ampl
    0.06
    Activations Density 0.019%

    No Known Activations