© 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. 15416
    Prev
    Next
    INDEX
    Explanations

    vitamin B names and deficiencies

    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
    å¹´åij³
    -0.08
    phis
    -0.08
     Trento
    -0.08
    空ä¸ŃçļĦ
    -0.08
    alous
    -0.07
    abay
    -0.07
    ë¡ł
    -0.07
     ÏĥÏħμÏĨ
    -0.07
    aglia
    -0.07
    -Trump
    -0.07
    POSITIVE LOGITS
     conversion
    0.08
     enzymes
    0.08
     convert
    0.08
     enzyme
    0.07
     converting
    0.07
    enzyme
    0.07
    ç¥ŀç»ı
    0.07
    convert
    0.07
     Conversion
    0.07
    éħ¶
    0.07
    Activations Density 0.028%

    No Known Activations