© 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. 22332
    Prev
    Next
    INDEX
    Explanations

    decision making

    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
    èĩªèº«å»ºè®¾
    -0.07
    åѦçĶŁçļĦåŃ¦ä¹ł
    -0.07
    é«ĺæ°Ķ
    -0.06
    å¨
    -0.06
    ynes
    -0.06
    ëıĻìĿ´
    -0.06
    _PIPE
    -0.06
    mpp
    -0.06
    æīĭ游ç½ij
    -0.06
    Appro
    -0.06
    POSITIVE LOGITS
    ä¸ŃçļĦéĩįè¦ģ
    0.09
    åĽłä¸ºä»ĸ们
    0.08
    对ä»ĸ们
    0.08
    cape
    0.08
    éĩįæĭħ
    0.08
    ãģ«åıĤåĬł
    0.08
    çIJ³å¨ľ
    0.08
    .Assign
    0.08
    对ä»ĸ们çļĦ
    0.08
    举足
    0.07
    Activations Density 0.515%

    No Known Activations