© 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. 24507
    Prev
    Next
    INDEX
    Explanations

    ancient, old, older, oldest

    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
    रà¥įफ
    -0.08
    vain
    -0.08
    адÑĮ
    -0.08
    .VK
    -0.08
    ServiceProvider
    -0.07
    æĽ´å¤ļ精彩åĨħ容
    -0.07
    æĪijå½ĵæŶ
    -0.07
    ÑħÑĢа
    -0.07
    Editors
    -0.07
    æĪIJåĬŁåIJİ
    -0.07
    POSITIVE LOGITS
     oldest
    0.14
    ä¹ħè¿ľ
    0.13
     older
    0.11
    æĤłä¹ħ
    0.11
    æĹ©
    0.11
    åı¤èĢģ
    0.11
     dating
    0.11
     ago
    0.11
    追溯åĪ°
    0.10
     earliest
    0.10
    Activations Density 0.275%

    No Known Activations