© 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. 12756
    Prev
    Next
    INDEX
    Explanations

    statistically significant

    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
    leta
    -0.08
    à¹Ĩ
    -0.08
    -shot
    -0.08
    ï¾ŀ
    -0.08
    鸳
    -0.08
    ieÅĦ
    -0.08
    -meter
    -0.08
    -stack
    -0.08
    -Day
    -0.08
    书ç½ij
    -0.08
    POSITIVE LOGITS
    jus
    0.07
    åĴĮ社ä¼ļ
    0.07
    ink
    0.06
    à¹Ģà¸Ńà¸ģ
    0.06
    åľ°éĽ·
    0.06
    ève
    0.06
    åĴĮç»ıæµİ
    0.06
    å¹¹
    0.06
    /environment
    0.06
    æľķ
    0.06
    Activations Density 0.018%

    No Known Activations