© 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. 42121
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols in equations

    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
    æĸĩåĵ²
    -0.08
    /fw
    -0.08
    anza
    -0.08
    æľ¬æ³ķ
    -0.08
     crumbs
    -0.08
    ÏĥÏĦι
    -0.08
    åıĮåıĮ
    -0.07
    wizard
    -0.07
    Ïĥμα
    -0.07
    ajo
    -0.07
    POSITIVE LOGITS
    éĩijå±±
    0.07
    eters
    0.07
    fold
    0.07
    yce
    0.06
    gos
    0.06
    enan
    0.06
    asurable
    0.06
    wirtschaft
    0.06
    rave
    0.06
    ainless
    0.06
    Activations Density 0.053%

    No Known Activations