© 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. 55327
    Prev
    Next
    INDEX
    Explanations

    solve equations containing 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
    émon
    -0.08
    пов
    -0.08
    Ĵáŀ
    -0.08
    efeld
    -0.07
    ftar
    -0.07
    确认åIJİ
    -0.07
    èİİæĭī
    -0.07
    ambi
    -0.07
    rame
    -0.07
    åħĥå¸ħ
    -0.07
    POSITIVE LOGITS
    -parse
    0.07
    çĹĽèĭ¦
    0.06
    ike
    0.06
    ÅŁtır
    0.06
    éħĴ
    0.06
    .parse
    0.06
     ÙģرÙĤ
    0.06
    gne
    0.06
    ../../../../
    0.06
    æ··åIJĪ
    0.06
    Activations Density 0.027%

    No Known Activations