© 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. 61164
    Prev
    Next
    INDEX
    Explanations

    we plus action verbs

    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
     "
    -0.07
    iciel
    -0.06
     "...
    -0.06
     advancements
    -0.06
    odos
    -0.06
    ".
    -0.06
    he
    -0.06
    çī©
    -0.06
    [
    -0.06
    äºļ
    -0.06
    POSITIVE LOGITS
    éķ¿æĮīè¯ĨåĪ«äºĮç»´çłģ
    0.08
    ä¸İæľ¬ç«Ļ
    0.07
    IMS
    0.07
    æĹ¥ä»¥ä¸Ĭ
    0.07
    æĺ¾èijĹæıIJåįĩ
    0.07
    èIJ¦
    0.07
    年以ä¸ĬçļĦ
    0.07
    tight
    0.07
    ffective
    0.07
    storm
    0.07
    Activations Density 0.004%

    No Known Activations