© 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. 16249
    Prev
    Next
    INDEX
    Explanations

    mathematical operations with numbers

    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
    hawks
    -0.07
     [&](
    -0.07
    çĤ¹åĩ»å¤įåĪ¶éĵ¾æİ¥
    -0.07
    alt
    -0.07
    åĤ¬
    -0.07
    çĵ¦å°Ķ
    -0.07
    ãĤ³ãĥł
    -0.07
    åİ»ä½ķ
    -0.07
     statt
    -0.07
    è¿Ļå°±è¦ģæ±Ĥ
    -0.07
    POSITIVE LOGITS
     numeral
    0.09
    符åı·
    0.09
    鼶ä¸ĭ
    0.08
    æķ°çļĦ
    0.08
    æķ°
    0.08
    温度计
    0.08
     negate
    0.08
     negative
    0.07
    åĩį
    0.07
     num
    0.07
    Activations Density 0.018%

    No Known Activations