© 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. 15886
    Prev
    Next
    INDEX
    Explanations

    multiple files / quantities

    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
    å¸ĮæľĽèĥ½å¤Łå¸®åĬ©
    -0.08
    好好
    -0.07
    "crypto
    -0.07
    cheon
    -0.07
    稽
    -0.06
    æĿ¥è¯´è¯´
    -0.06
    å¥½å¥½åľ°
    -0.06
    OURCES
    -0.06
    ERM
    -0.06
    æĪĸå¤ļæĪĸå°ij
    -0.06
    POSITIVE LOGITS
     instantly
    0.17
     ÑģÑĢазÑĥ
    0.16
    æĹłéľĢ
    0.16
     immediately
    0.15
     quickly
    0.15
    缴æİ¥åľ¨
    0.14
     without
    0.13
    à¹Ĥà¸Ķยà¹Ħมà¹Īà¸ķà¹īà¸Ńà¸ĩ
    0.13
    ä¸įçĶ¨åĨį
    0.13
     rapidamente
    0.13
    Activations Density 0.691%

    No Known Activations