© 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. 18093
    Prev
    Next
    INDEX
    Explanations

    Pauli-Lubanski operator equations

    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
    uskan
    -0.07
    orno
    -0.07
    欣欣
    -0.06
     müh
    -0.06
    plevel
    -0.06
    åĪĨ享åĨħ容
    -0.06
    رس
    -0.06
    _ts
    -0.06
    úz
    -0.06
    ë¡ľëĬĶ
    -0.06
    POSITIVE LOGITS
    instein
    0.08
    regon
    0.08
    wart
    0.08
     appunto
    0.08
    áºŃy
    0.07
    agh
    0.07
     Moran
    0.07
    å¹³çĶŁ
    0.07
    ëĮĢë¡ľ
    0.07
     apro
    0.07
    Activations Density 0.012%

    No Known Activations