© 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. 32883
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    梳
    -0.08
    comb
    -0.08
    oul
    -0.07
    opian
    -0.07
    å¿ĥäºĨ
    -0.07
    ç»Łè®¡å±Ģ
    -0.07
    以任ä½ķ
    -0.07
    ä¸įå¾Ĺä»İäºĭ
    -0.07
    æĹ¥æ¶Īæģ¯
    -0.07
    tty
    -0.06
    POSITIVE LOGITS
    大大å°ı
    0.08
    æ³Ľ
    0.07
    watan
    0.07
    大大
    0.06
    usal
    0.06
    ints
    0.06
    åģļéĶĻ
    0.06
    çij¶
    0.06
    usta
    0.06
    .scale
    0.06
    Activations Density 0.000%

    No Known Activations