© 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. 13568
    Prev
    Next
    INDEX
    Explanations

    1) Field of the Invention

    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
    xce
    -0.07
    æĭ§
    -0.07
    ânt
    -0.07
    ujan
    -0.07
    ÓĻне
    -0.06
    avant
    -0.06
    @protocol
    -0.06
    å¾®èĸĦ
    -0.06
    esi
    -0.06
    ä¸į严
    -0.06
    POSITIVE LOGITS
    ãĢĢ
    0.07
    inc
    0.07
    0.07
    å¨ĩ
    0.07
    ´
    0.07
    åĩ¡æľ¬ç½ij注æĺİ
    0.06
    绪
    0.06
     firstly
    0.06
    okus
    0.06
    衣裳
    0.06
    Activations Density 0.006%

    No Known Activations