© 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. 43511
    Prev
    Next
    INDEX
    Explanations

    addition and subtraction of 2-digit numbers

    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
    éĵ¿
    -0.08
    aily
    -0.07
     Shr
    -0.06
     closed
    -0.06
    é¢ĦåħĪ
    -0.06
    гло
    -0.06
    /gcc
    -0.06
    大çĽĺ
    -0.06
    æµģè¿ŀ
    -0.06
     Faust
    -0.06
    POSITIVE LOGITS
    caff
    0.08
     Moraes
    0.08
    縱
    0.08
    é¾Ħ
    0.08
    -pad
    0.07
    éģ·
    0.07
    ä¸Ģè¡Į
    0.07
    é¢ľ
    0.07
    opp
    0.07
    ÑĤÑģÑı
    0.07
    Activations Density 0.006%

    No Known Activations