© 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. 16798
    Prev
    Next
    INDEX
    Explanations

    document structure and guidelines

    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
    asser
    -0.09
    Ỽm
    -0.08
     ìķĦëĭĪë©´
    -0.08
    assin
    -0.08
    æĪĸå¤ļ个
    -0.07
    京åħ¬ç½ijå®īå¤ĩ
    -0.07
    èĩªçĦ¶èĢĮ
    -0.07
    ä¸ĭåIJĮ
    -0.07
    æĬĬ
    -0.07
    æĪĸèĢħåħ¶ä»ĸ
    -0.07
    POSITIVE LOGITS
    åıĬè¦ģæ±Ĥ
    0.08
    [Y
    0.07
    åĪĨæŀIJåıĬ
    0.06
    åıĬ管çIJĨ
    0.06
    åıĬåħ¶åºĶçĶ¨
    0.06
    :
    0.06
    åıĬåħ¶
    0.06
    ï¼ļ
    0.06
    åĮħ
    0.06
    åıĬåºĶçĶ¨
    0.06
    Activations Density 0.121%

    No Known Activations