© 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. 9719
    Prev
    Next
    INDEX
    Explanations

    listing items or instructions

    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
    -0.07
    >:</
    -0.07
    æĺ¯ä»Ģä¹Īåij¢
    -0.07
    ä¼ĹæīĢåij¨çŁ¥
    -0.07
    éĤ£æł·çļĦ
    -0.07
     Firstly
    -0.06
    à¸ĩ
    -0.06
    amic
    -0.06
    æİ¥ä¸ĭæĿ¥
    -0.06
    æīĢ以å½ĵ
    -0.06
    POSITIVE LOGITS
    çĮķçĮ´
    0.08
    θÏģÏī
    0.07
    ness
    0.07
    нÑĮ
    0.07
    osan
    0.07
    ward
    0.07
    VOKE
    0.07
    èĽī
    0.07
    éģĩäºĭ
    0.07
    ries
    0.07
    Activations Density 0.014%

    No Known Activations