© 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. 31364
    Prev
    Next
    INDEX
    Explanations

    ratios, differences, or operations like times, plus, minus

    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
    оÑģоб
    -0.09
    æ¯ı天éĥ½è¦ģ
    -0.07
    éķ¿çº¦
    -0.07
    æķĻä½łå¦Ĥä½ķ
    -0.07
    å«Įçĸij
    -0.07
    ced
    -0.07
    req
    -0.07
     Feliz
    -0.07
    éļıçĿĢ社ä¼ļ
    -0.07
    [".
    -0.07
    POSITIVE LOGITS
    çŃīäºİ
    0.09
    åĨįåĬłä¸Ĭ
    0.09
     minus
    0.08
     times
    0.08
     optionally
    0.07
    åĨį
    0.06
    åĬłä¸Ĭ
    0.06
    å©Ĩ
    0.06
    udi
    0.06
     plus
    0.06
    Activations Density 0.020%

    No Known Activations