© 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. 19203
    Prev
    Next
    INDEX
    Explanations

    currency 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
    åıĬ管çIJĨ
    -0.07
     gern
    -0.07
     serta
    -0.07
     amongst
    -0.06
    æĭĽåij¼
    -0.06
    ãĥĿãĥ³
    -0.06
    /dis
    -0.06
    /report
    -0.06
    æľīåģ¿
    -0.06
    /up
    -0.06
    POSITIVE LOGITS
    ¬ģ
    0.07
    Ń
    0.07
    '&&
    0.07
     libra
    0.07
    ÑĢаÑĨиÑı
    0.07
    ÙĬاج
    0.07
    pira
    0.07
     âĤ¬,
    0.07
    Ú©ÙĪر
    0.07
    åºĵéĩĮ
    0.07
    Activations Density 0.016%

    No Known Activations