© 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. 14531
    Prev
    Next
    INDEX
    Explanations

    differences and variability

    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
     count
    -0.07
    æľŁéĹ´
    -0.07
    à¹īà¸Ńà¸Ļ
    -0.07
     cim
    -0.06
    ETE
    -0.06
    arella
    -0.06
    ãĥ¼ãĥĹ
    -0.06
     Tho
    -0.06
    åīį身
    -0.06
    ç»ĵæŀĦä¸Ń
    -0.06
    POSITIVE LOGITS
     differences
    0.14
    å·®å¼ĤåĮĸ
    0.13
    éĴĪ对ä¸įåIJĮ
    0.13
    å·®å¼ĤæĢ§
    0.13
    å·®å¼Ĥ
    0.13
    ifferences
    0.12
    åĽłåľ°åĪ¶å®ľ
    0.12
     Differences
    0.12
     differing
    0.11
    对ä¸įåIJĮ
    0.11
    Activations Density 0.144%

    No Known Activations