© 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. 17163
    Prev
    Next
    INDEX
    Explanations

    regard or against or association

    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
    imonial
    -0.07
    erste
    -0.07
    ible
    -0.07
    åģļçļĦå°±æĺ¯
    -0.07
    è¯ģæį®è¯ģæĺİ
    -0.06
    scha
    -0.06
    ео
    -0.06
    çļĦçݰ象
    -0.06
    imonials
    -0.06
    _PROPERTIES
    -0.06
    POSITIVE LOGITS
    äºİè¡Į
    0.11
    égard
    0.09
     against
    0.09
    äºİ
    0.09
    à¸ģัà¸ļà¸ģาร
    0.09
     regard
    0.08
    äºİäºĭ
    0.08
    å¾ĹçĽĬ
    0.08
    å®ļäºİ
    0.08
    ä¹İåħ¶
    0.08
    Activations Density 0.604%

    No Known Activations