© 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. 47731
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and problem solving phrases

    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
     fra
    -0.07
    æ¢Ń
    -0.06
    ел
    -0.06
    el
    -0.06
    oria
    -0.06
    åĦ¿
    -0.06
    stan
    -0.06
    çº¢é¢ľ
    -0.06
    elan
    -0.06
    erts
    -0.06
    POSITIVE LOGITS
    ç¯ĩä¸Ģ
    0.08
    æł©
    0.08
    å¼Ģå±ķ好
    0.07
    침
    0.07
    è£ħç®±
    0.07
    isir
    0.07
    带åİ»
    0.07
    жиÑĤелÑĮ
    0.07
    .overflow
    0.07
    Regarding
    0.07
    Activations Density 0.001%

    No Known Activations