© 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. 33585
    Prev
    Next
    INDEX
    Explanations

    making things easier and better

    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
    è°ģæĿ¥
    -0.07
     겸
    -0.07
    nico
    -0.07
    å¿ĥçľ¼
    -0.07
    å¦Ĥä½ķéĢļè¿ĩ
    -0.07
    (pat
    -0.07
    并éĢļè¿ĩ
    -0.07
    ÑĢекÑĤи
    -0.07
    è¿ĻçĤ¹
    -0.06
    éĢĻä¸Ģé»ŀ
    -0.06
    POSITIVE LOGITS
    ideshow
    0.09
     {}:
    0.08
    igl
    0.08
    лли
    0.08
    ennen
    0.07
    顺åĪ©
    0.07
     functioning
    0.07
     Gelt
    0.07
    .nih
    0.07
     future
    0.07
    Activations Density 0.447%

    No Known Activations