© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2459
    Prev
    Next
    INDEX
    Explanations

    software documentation and examples

    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
     Sama
    -0.08
    amo
    -0.07
    MBED
    -0.07
    asilan
    -0.07
     umo
    -0.07
    agam
    -0.07
    landet
    -0.07
    mue
    -0.07
    书åŁİ
    -0.06
    å¤ļç§įæĸ¹å¼ı
    -0.06
    POSITIVE LOGITS
    æķ´çIJĨ
    0.09
    IZE
    0.08
    æķ´æ´ģ
    0.08
    æķ´çIJĨçļĦ
    0.08
     consolid
    0.07
    æŃ£å¼ı
    0.07
    æŃ£å¼ıçļĦ
    0.07
    oup
    0.07
     clearer
    0.07
    æķ´çIJĨäºĨ
    0.07
    Activations Density 0.011%

    No Known Activations