© 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. 39939
    Prev
    Next
    INDEX
    Explanations

    stenosis

    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
    èĿł
    -0.09
    éĵIJ
    -0.08
    éģľ
    -0.08
    汽车ä¹ĭ家
    -0.08
    身ä¸Ĭä¸ĭ
    -0.07
    UDA
    -0.07
    æħ·
    -0.07
    宵
    -0.07
    å¿ĥçĶĺ
    -0.07
    碩
    -0.07
    POSITIVE LOGITS
    å¦ĩ人
    0.10
    管åŃIJ
    0.07
     unto
    0.07
    æĿĢ人
    0.07
    è¡£æľį
    0.07
    åįĹéĺ³
    0.07
    礼æĭľ
    0.07
    女åŃIJ
    0.07
    èįĨå·ŀ
    0.07
    çIJħçIJĬ
    0.07
    Activations Density 0.001%

    No Known Activations