© 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. 11188
    Prev
    Next
    INDEX
    Explanations

    acid or related suffixes

    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
    اÛĮØ´
    -0.09
    Ù°
    -0.09
    olation
    -0.08
     Äijặn
    -0.08
    elman
    -0.08
    èĢĮå°±
    -0.08
    åĴĮåİ¿
    -0.08
    íĮ
    -0.07
    Åijd
    -0.07
    翼翼
    -0.07
    POSITIVE LOGITS
    ate
    0.08
    åĸ°
    0.07
    ../../
    0.07
    ycl
    0.07
    eres
    0.07
    à§įত
    0.07
    aceous
    0.07
    ÙĬÙĦÙĬØ©
    0.07
    евиÑĩ
    0.07
    à¹Īาย
    0.06
    Activations Density 0.001%

    No Known Activations