© 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. 11950
    Prev
    Next
    INDEX
    Explanations

    for each iteration

    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
    å²Ń
    -0.09
    说æĺ¯
    -0.08
    utang
    -0.08
    ãĥ¶
    -0.08
    åª
    -0.08
    unde
    -0.07
    oload
    -0.07
     Rohr
    -0.07
    uci
    -0.07
    æ±Łä¸ľ
    -0.07
    POSITIVE LOGITS
     iter
    0.07
     sequentially
    0.07
     incoming
    0.07
     từng
    0.06
     upcoming
    0.06
     successive
    0.06
     consecutive
    0.06
     simulated
    0.06
    è¯Ħ
    0.06
    éģįåıĬ
    0.06
    Activations Density 0.008%

    No Known Activations