© 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. 15350
    Prev
    Next
    INDEX
    Explanations

    oxygen activation or atmosphere

    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
    γÏĮ
    -0.07
    èī²åĪĹ
    -0.07
    西æĸ¯
    -0.07
    (SYS
    -0.07
    pedo
    -0.07
    anical
    -0.07
    clid
    -0.07
    æī«çłģåħ³æ³¨
    -0.07
    åĨ³å®ļ书
    -0.07
    åIJijæĹ¥
    -0.07
    POSITIVE LOGITS
    icana
    0.07
    arend
    0.07
    agno
    0.07
    oros
    0.07
     mole
    0.06
    ernes
    0.06
    icano
    0.06
     Fleet
    0.06
    åħ«æĸ¹
    0.06
     lÆ°Æ¡ng
    0.06
    Activations Density 0.013%

    No Known Activations