© 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. 39249
    Prev
    Next
    INDEX
    Explanations

    company name suffixes or types

    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
    [Math
    -0.07
    vind
    -0.07
    æĺı
    -0.07
    æľīçļĦåIJĮåѦ
    -0.06
    æĮĸæİĺåħ¬åı¸
    -0.06
    åѦåĪ¶
    -0.06
    vain
    -0.06
    éļı身
    -0.06
    Interop
    -0.06
     Sebasti
    -0.06
    POSITIVE LOGITS
    éĿ¢åIJij
    0.08
    çĻ»éĮ²
    0.07
    ners
    0.07
    éĿ¢åIJijåħ¨åĽ½
    0.07
    ng
    0.07
    ÃŃp
    0.07
    enzhen
    0.07
    åĨį说
    0.07
     Cave
    0.07
    对å¤ĸè´¸æĺĵ
    0.07
    Activations Density 0.058%

    No Known Activations