© 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. 8135
    Prev
    Next
    INDEX
    Explanations

    efficiency, low power consumption

    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
    åŃ¦ä¹łæķĪæŀľ
    -0.07
    پر
    -0.07
    è¾ľ
    -0.07
    باÙĨ
    -0.07
    apolis
    -0.07
    echt
    -0.07
    ä¹Łåı¯èĥ½æĺ¯
    -0.07
    åħ³äºİåĬłå¼º
    -0.06
     TOO
    -0.06
    å¤ıæĹ¥
    -0.06
    POSITIVE LOGITS
     inherently
    0.10
    ä¸įæ¶īåıĬ
    0.09
    åıªéľĢè¦ģ
    0.08
     inherent
    0.08
    ä»İæł¹æľ¬ä¸Ĭ
    0.08
    ixa
    0.08
    ä½łåıªè¦ģ
    0.08
    åıªéľĢ
    0.07
    éĥ½æľīèĩªå·±çļĦ
    0.07
    DLL
    0.07
    Activations Density 0.086%

    No Known Activations