© 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. 21063
    Prev
    Next
    INDEX
    Explanations

    subtracting 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
    ç³»çļĦ
    -0.07
    åIJĦéĥ¨
    -0.07
    ç»ķ
    -0.07
     reins
    -0.06
    -0.06
    ç¹ŀ
    -0.06
    izable
    -0.06
    æī¬çļĦ
    -0.06
    abler
    -0.06
    åºĵå°Ķ
    -0.06
    POSITIVE LOGITS
    ArrayOf
    0.07
    å½¼æѤçļĦ
    0.07
    apat
    0.07
    ä¸įæĢ¥
    0.07
    -extra
    0.07
    åĬŀåıij
    0.07
    åĴĮæĢĿèĢĥ
    0.07
     Earn
    0.07
    shan
    0.07
    THR
    0.07
    Activations Density 0.003%

    No Known Activations