© 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. 29064
    Prev
    Next
    INDEX
    Explanations

    reciprocal relationships

    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
    æĹŃæĹ¥
    -0.10
    ETR
    -0.07
    PropertyValue
    -0.07
    erten
    -0.07
    _fds
    -0.07
    åħ¬åħ±é¢Ħç®Ĺ
    -0.06
    ä¸įèĢģ
    -0.06
     jig
    -0.06
     oldValue
    -0.06
    erden
    -0.06
    POSITIVE LOGITS
     reciprocal
    0.10
    åıįè¿ĩæĿ¥
    0.10
     recipro
    0.10
     recip
    0.10
     complementary
    0.09
    äºĴ为
    0.08
    çļĦåıį
    0.08
     اÙĦÙħÙĤابÙĦ
    0.08
    äºĴè¡¥
    0.08
    èIJ¤
    0.08
    Activations Density 0.005%

    No Known Activations