© 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. 7547
    Prev
    Next
    INDEX
    Explanations

    profit and loss

    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
    åħįè´¹é¢Ĩåıĸ
    -0.07
    æĶ¯ä»ĺè¿Łå»¶å±¥è¡Į
    -0.07
    宪
    -0.06
    èĤ¡æĿĥåĩºè´¨
    -0.06
    supply
    -0.06
     Choir
    -0.06
    çĸijä¼¼è¿Ŀè§Ħ
    -0.06
    å¯Ĩ度
    -0.06
    亿人
    -0.06
    .Ag
    -0.06
    POSITIVE LOGITS
    ìĿµ
    0.11
     losses
    0.09
    æįŁå¤±çļĦ
    0.08
     nette
    0.08
     matur
    0.08
    åĪ©çļĦ
    0.08
    æįŁçĽĬ
    0.07
    _ISR
    0.07
    波段
    0.07
     loss
    0.07
    Activations Density 0.014%

    No Known Activations