© 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. 12743
    Prev
    Next
    INDEX
    Explanations

    mathematical sums

    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
    ÙĨدÙĩ
    -0.08
    ãĤ£
    -0.08
    ebab
    -0.07
    obb
    -0.07
    gina
    -0.07
    orr
    -0.07
    à§ĩà¦ķ
    -0.07
    åİ®
    -0.06
    dei
    -0.06
    à§įস
    -0.06
    POSITIVE LOGITS
    æ°´åĻ¨
    0.08
    æľ¬æ¥¼
    0.07
    aphore
    0.07
    ÛĮ
    0.07
    çĻ¾å·Ŀ
    0.07
    sic
    0.07
    à¹īาà¸Ļ
    0.07
    êtement
    0.07
    åĮĹæµ·
    0.07
    latt
    0.07
    Activations Density 0.006%

    No Known Activations