© 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. 50263
    Prev
    Next
    INDEX
    Explanations

    names with suffixes like Jr. or Cord

    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
    unk
    -0.07
    unks
    -0.06
    å¼Ģå±ķ好
    -0.06
    .configure
    -0.06
    æĸĩåĮĸçŁ¥è¯Ĩ
    -0.06
    zec
    -0.06
    åı¯ä»¥ä¿ĥè¿Ľ
    -0.06
    DIR
    -0.06
    åįģæĸ¹
    -0.06
    å¾®
    -0.06
    POSITIVE LOGITS
     Daly
    0.08
    -peer
    0.08
    西æŀĹ
    0.07
     اÙĦتÙħÙĪ
    0.07
    Ĥ¬
    0.07
     Peker
    0.07
    óc
    0.07
    ey
    0.07
    ippets
    0.07
    amenti
    0.07
    Activations Density 0.736%

    No Known Activations