© 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. 21466
    Prev
    Next
    INDEX
    Explanations

    energy transferred, stored, or lost

    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
    aisy
    -0.08
     pan
    -0.08
    esy
    -0.08
     diranc
    -0.08
     dituj
    -0.08
    ovo
    -0.07
    èĴĻå¾·
    -0.07
    åŀ¢
    -0.07
    ме
    -0.07
    ynes
    -0.07
    POSITIVE LOGITS
    ä¸Ģéĥ¨åĪĨ
    0.10
    转åĮĸæĪIJ
    0.09
    转åĮĸ为
    0.09
     transferred
    0.08
     redistributed
    0.08
    æľīä¸Ģéĥ¨åĪĨ
    0.08
     convertible
    0.08
    สà¹Īวà¸Ļ
    0.08
     absorbed
    0.08
     lost
    0.07
    Activations Density 0.009%

    No Known Activations