© 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. 28253
    Prev
    Next
    INDEX
    Explanations

    lace kimono

    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
    éĴ£éĩij
    -0.08
    ewel
    -0.07
    æī¾ä½ł
    -0.07
    éĶĻè¿ĩ
    -0.07
    纯粹çļĦ
    -0.06
    å®Įåħ¨æĺ¯
    -0.06
    -pocket
    -0.06
    ÏĢοÏĤ
    -0.06
    追究
    -0.06
    æľªç»ı
    -0.06
    POSITIVE LOGITS
    åIJ«éĩıçļĦ
    0.08
    é£İæł¼çļĦ
    0.07
    ulated
    0.07
     многое
    0.07
    çī¹æĢ§çļĦ
    0.07
     Everything
    0.07
    åIJĦå¼ı
    0.07
    æŃ¤èµ·
    0.07
    尼奥
    0.07
    忱
    0.07
    Activations Density 0.294%

    No Known Activations