© 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. 39540
    Prev
    Next
    INDEX
    Explanations

    combination generation or change

    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
    segue
    -0.08
    åľ³
    -0.08
    kees
    -0.08
     Simak
    -0.08
    ynchronize
    -0.08
     cuckold
    -0.07
    urname
    -0.07
    èĬ±ä¸Ģ
    -0.07
    æķ°æį®å¤ĦçIJĨ
    -0.07
    é»Ħæ²¹
    -0.07
    POSITIVE LOGITS
     combinations
    0.09
    ç»ĦåIJĪ
    0.08
    çµĦåIJĪ
    0.08
    çļĦç»ĦåIJĪ
    0.07
    pel
    0.07
     combination
    0.07
    æķĪçİĩ
    0.07
    æīĢçĶ¨
    0.07
     denomin
    0.07
     Combination
    0.07
    Activations Density 0.005%

    No Known Activations