© 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. 62042
    Prev
    Next
    INDEX
    Explanations

    data structures, lists, sequences

    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
    æIJŃ
    -0.08
    é£ŀ鸣
    -0.07
    æľĪåħī
    -0.07
    æľĪçĶŁ
    -0.07
    orman
    -0.07
    å°½äºĨ
    -0.06
    erah
    -0.06
    YO
    -0.06
    armed
    -0.06
    å°½
    -0.06
    POSITIVE LOGITS
    æľ¬ç«Ļ
    0.08
    é¢Ħå¤ĦçIJĨ
    0.07
     preprocess
    0.07
     preprocessing
    0.07
    å§ĵ
    0.07
    inery
    0.07
    ardy
    0.07
    åİŁå§ĭ
    0.07
    æ¶Ĥä¸Ĭ
    0.06
    .Convert
    0.06
    Activations Density 0.008%

    No Known Activations