© 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. 49539
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and symbols

    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
    otte
    -0.08
    oup
    -0.08
    μή
    -0.07
     brod
    -0.07
    =index
    -0.07
    åIJİéĢĢ
    -0.07
    ocie
    -0.07
    éŃģ
    -0.07
    Whatever
    -0.07
     cất
    -0.07
    POSITIVE LOGITS
    fone
    0.07
     ÏĥÏħνα
    0.06
     competit
    0.06
     pools
    0.06
     Life
    0.06
     poll
    0.06
    izio
    0.06
    สมา
    0.06
    éĩĮåħĭ
    0.06
    affen
    0.06
    Activations Density 0.008%

    No Known Activations