© 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. 48577
    Prev
    Next
    INDEX
    Explanations

    acronyms and definitions

    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
    è¾Ľäº¥
    -0.07
     gro
    -0.07
    å°±ä¸ļåīįæĻ¯
    -0.07
    linky
    -0.07
    —or
    -0.06
    ógica
    -0.06
    åı¯æĮģç»Ńåıijå±ķçļĦ
    -0.06
    æľīä»»ä½ķçĸijéĹ®
    -0.06
    avor
    -0.06
    {/
    -0.06
    POSITIVE LOGITS
    .;
    0.08
    ;.
    0.07
    rik
    0.07
    ;"
    0.07
    aczy
    0.07
    ï¼Ľ
    0.07
    -border
    0.07
     "";
    0.07
     ;
    0.06
    ;border
    0.06
    Activations Density 0.025%

    No Known Activations