© 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. 31519
    Prev
    Next
    INDEX
    Explanations

    subtracting numbers or dates

    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
    azzi
    -0.07
    åľ°åĿĢä½įäºİ
    -0.07
    PPER
    -0.07
    ensuu
    -0.06
    èĥ½æīĵ
    -0.06
    aina
    -0.06
    elling
    -0.06
    æĿ¥çĶµåĴ¨è¯¢
    -0.06
    çµIJåIJĪ
    -0.06
    à¹Ģà¸Ĭà¹Īà¸Ļà¸Ļัà¹īà¸Ļ
    -0.06
    POSITIVE LOGITS
     hinzu
    0.15
    éĢĤéĩıçļĦ
    0.10
    æĥħåĨµåIJİ
    0.09
    ãĤĴåĬł
    0.09
     thêm
    0.08
    æĸ¹æ³ķæĿ¥
    0.08
    bole
    0.08
    éĢĤéĩı
    0.08
     ÑĩÑĤобÑĭ
    0.08
    çļĦæĸ¹æ³ķæĿ¥
    0.08
    Activations Density 0.029%

    No Known Activations