© 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. 39015
    Prev
    Next
    INDEX
    Explanations

    Irish actress

    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
    kho
    -0.08
    妩åªļ
    -0.07
    asaran
    -0.07
    ibaba
    -0.07
    arez
    -0.07
    TypeDef
    -0.07
    ä¹Łä¸įä¸Ģå®ļ
    -0.07
     Bamboo
    -0.07
    ç½ijçĬ¶
    -0.07
    adiran
    -0.07
    POSITIVE LOGITS
    æŃ£æĺ¯
    0.08
    ãģĭãĤīãģĵãģĿ
    0.07
    ommel
    0.07
    .closest
    0.07
    æĬ¥è®°èĢħ
    0.07
     proprio
    0.06
    为éĩį
    0.06
    人åħ³æ³¨
    0.06
     wÅĤaÅĽnie
    0.06
    nic
    0.06
    Activations Density 0.127%

    No Known Activations