© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 3117
    Prev
    Next
    INDEX
    Explanations

    fly before career

    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
    æľ¬æ³ķ
    -0.10
    ä¸ĭåľº
    -0.09
    ww
    -0.08
    ža
    -0.08
    addock
    -0.08
    èݱæĸ¯
    -0.08
    ä¸į缸åIJĮ
    -0.08
    åĨħå¿ĥä¸ĸçķĮ
    -0.08
    çĪ±ä¸į
    -0.08
     Äijông
    -0.08
    POSITIVE LOGITS
    ç¹ģ
    0.07
    ãģ¤ãģį
    0.07
     either
    0.07
    è¦ģä¹Īæĺ¯
    0.07
    çľ·
    0.07
    inee
    0.07
     Either
    0.06
    either
    0.06
    Either
    0.06
     Rowe
    0.06
    Activations Density 0.009%

    No Known Activations