© 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. 64471
    Prev
    Next
    INDEX
    Explanations

    general business and technical terms

    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
    饶
    -0.07
     Blade
    -0.07
    arki
    -0.07
    第ä¹Ŀå±Ĭ
    -0.06
     Bres
    -0.06
    æĬĬäºĭæĥħ
    -0.06
    \Config
    -0.06
     modular
    -0.06
    ì¹Ń
    -0.06
    èģĮä¸ļæĬĢæľ¯
    -0.06
    POSITIVE LOGITS
     unrelated
    0.12
    general
    0.10
    çļĦåħ¶ä»ĸ
    0.09
     general
    0.09
     broader
    0.09
    éĢļçĶ¨çļĦ
    0.09
     GENERAL
    0.09
    _general
    0.09
    GENERAL
    0.08
    åħ¶å®ĥ
    0.08
    Activations Density 0.901%

    No Known Activations