© 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. 25583
    Prev
    Next
    INDEX
    Explanations

    Appellant, v. GENERAL ELECTRIC CO

    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
    -0.11
     ä»ĬæĹ¥
    -0.08
    asikan
    -0.08
    eni
    -0.08
    ková
    -0.08
    adak
    -0.07
    agina
    -0.07
    ickle
    -0.07
    à¸łà¸´
    -0.07
     CONCAT
    -0.07
    POSITIVE LOGITS
    åĭĩå¾Ģ缴åīį
    0.07
    åħ¢åħ¢ä¸ļä¸ļ
    0.07
    äºĭåįĬåĬŁåĢį
    0.07
    elic
    0.06
     Nicol
    0.06
    ilton
    0.06
    ä¸įåı¯æĢĿè®®
    0.06
    æĬĬåŃ©åŃIJ
    0.06
    æī
    0.06
    箫
    0.06
    Activations Density 0.592%

    No Known Activations