© 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. 55980
    Prev
    Next
    INDEX
    Explanations

    list formatting or punctuation

    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°±æĺ¯äºĨ
    -0.08
    agoza
    -0.07
    对ä¸Ĭè¿°
    -0.07
    åľ¨è¿Ļä¸Ģ
    -0.07
     Lega
    -0.06
    áĢ¬
    -0.06
    izoph
    -0.06
    enÃŃ
    -0.06
    ίÏĥ
    -0.06
    æĪĪ
    -0.06
    POSITIVE LOGITS
     _____
    0.08
    ､
    0.07
     ____
    0.07
    丽åįİ
    0.07
     _______,
    0.07
    âĢIJ
    0.07
    __$
    0.07
     ________
    0.07
     ______
    0.07
    ï¼Ĭ
    0.07
    Activations Density 0.028%

    No Known Activations