© 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. 58425
    Prev
    Next
    INDEX
    Explanations

    electrical power inverters

    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
     Globals
    -0.07
     foregoing
    -0.07
    —including
    -0.07
    è¶Ł
    -0.07
    .observe
    -0.07
    Train
    -0.06
    以ä¸Ĭ
    -0.06
    tei
    -0.06
    çݺ
    -0.06
    —even
    -0.06
    POSITIVE LOGITS
    åīįèĢħ
    0.11
    åĪĨåĪ«
    0.11
     respectively
    0.10
    åĪĨåĪ¥
    0.10
    åĪĨåĪ«åľ¨
    0.09
    è¿Ļ两ç§į
    0.09
    åĪĨåĪ«ä¸İ
    0.09
    ãģ¨ãĤĤãģ«
    0.09
    åĪĨåĪ«æĺ¯
    0.09
    åĪĨåĪ«ä¸º
    0.09
    Activations Density 0.193%

    No Known Activations