© 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. 28419
    Prev
    Next
    INDEX
    Explanations

    electronic devices and computing

    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
    ä¸īé¤IJ
    -0.07
    éĢļå¸¸åľ¨
    -0.07
    åħ¸åŀĭ
    -0.07
    à¹ģà¸Ĺà¹ī
    -0.07
    wl
    -0.07
     MDF
    -0.07
    stal
    -0.07
    æ·¹
    -0.07
    åĬªåĬĽä¸º
    -0.07
     coy
    -0.07
    POSITIVE LOGITS
    æľªæĿ¥çļĦ
    0.11
    ä¸ĭä¸Ģ代
    0.09
     future
    0.09
    çļĦæľªæĿ¥
    0.09
     feats
    0.09
    ä¸įä¹ħçļĦå°ĨæĿ¥
    0.09
     futuro
    0.08
     бÑĥдÑĥÑīего
    0.08
    æľªä¾ĨçļĦ
    0.08
     unprecedented
    0.08
    Activations Density 0.356%

    No Known Activations