© 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. 13620
    Prev
    Next
    INDEX
    Explanations

    CA, origin, incomes, real, today, Jesus

    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
    çĶŁåŃ©åŃIJ
    -0.08
    è¿ĶåĽŀåĪĹ表
    -0.08
    TypeName
    -0.07
    oux
    -0.07
     (*)(
    -0.07
    wdx
    -0.07
    ä¸ŃçļĦä¸Ģç§į
    -0.07
    naie
    -0.07
    anging
    -0.07
    óÅĤ
    -0.07
    POSITIVE LOGITS
     itself
    0.10
    æľ¬èº«
    0.09
    æľ¬èº«çļĦ
    0.09
    èĩªèº«
    0.08
    åıįæŃ£
    0.07
    heim
    0.07
    æľ¬èº«å°±æĺ¯
    0.07
    ä¸įåĬ¨
    0.06
    edit
    0.06
     lê
    0.06
    Activations Density 0.013%

    No Known Activations