© 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. 45668
    Prev
    Next
    INDEX
    Explanations

    activates or suppresses activity

    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
    mitt
    -0.07
    代çIJĨ
    -0.07
     Wyn
    -0.06
    åĪĨå·¦åı³
    -0.06
     Weekend
    -0.06
    kaar
    -0.06
    家æĺ¯
    -0.06
    Serialize
    -0.06
     Wiki
    -0.06
    /
    -0.06
    POSITIVE LOGITS
     ataupun
    0.09
    yam
    0.08
     maupun
    0.08
    ostro
    0.08
    resses
    0.08
    åĿIJä¸ĭ
    0.08
    estand
    0.08
    翻天
    0.07
    æĬķèµĦæĪĸ
    0.07
    åĽ¾çīĩæĪĸ
    0.07
    Activations Density 0.091%

    No Known Activations