© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 57201
    Prev
    Next
    INDEX
    Explanations

    by word

    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
    å°Ĩè¿Ļ
    -0.08
    nev
    -0.07
    ikli
    -0.07
    对ä¸Ĭè¿°
    -0.07
    æĸ°è§Ħå®ļ
    -0.07
    解åĨ³éĹ®é¢ĺçļĦ
    -0.07
    å°ĨæĪij
    -0.07
    便å°Ĩ
    -0.07
    ç²¾è¯ļ
    -0.07
    éĢļè¿ĩ以ä¸Ĭ
    -0.07
    POSITIVE LOGITS
    —including
    0.08
    âĢIJ
    0.08
    漪
    0.08
    including
    0.07
    !--
    0.07
    æĺ¯ä¸įæĺ¯
    0.07
     basically
    0.07
    ~-
    0.07
    —who
    0.06
    ––
    0.06
    Activations Density 0.009%

    No Known Activations