© 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. 30784
    Prev
    Next
    INDEX
    Explanations

    Montenegro

    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
    对ä¸Ĭè¿°
    -0.06
     übrigens
    -0.06
    jte
    -0.06
    onej
    -0.06
    —all
    -0.05
    åĽłä¸ºè¿ĻäºĽ
    -0.05
    onel
    -0.05
    å¦ĤæĤ¨
    -0.05
    éĿ¢ç§¯è¾¾
    -0.05
    Ñİд
    -0.05
    POSITIVE LOGITS
    è±ģ
    0.07
    æĮģä¹ĭ以
    0.07
    <unk
    0.07
    antara
    0.07
    婺
    0.07
    ä¹Łä¸įä¾ĭå¤ĸ
    0.07
    okka
    0.07
    ÙĬدÙĩ
    0.06
    许许å¤ļ
    0.06
    беÑĢкÑĥ
    0.06
    Activations Density 2.826%

    No Known Activations