© 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. 40780
    Prev
    Next
    INDEX
    Explanations

    spin and spectral lines

    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
     gradient
    -0.07
    ugging
    -0.07
    çİ¯å²Ľ
    -0.07
    ζη
    -0.07
    ikh
    -0.07
    å²±
    -0.07
     Gradient
    -0.06
     duty
    -0.06
    вай
    -0.06
     human
    -0.06
    POSITIVE LOGITS
    Spin
    0.08
     Spin
    0.08
    spin
    0.08
     spin
    0.07
    /ion
    0.07
    states
    0.07
     Ø®ÙĪØ´
    0.07
    æİł
    0.07
    åIJĦæĹı
    0.07
    οÏħÏģγ
    0.07
    Activations Density 0.001%

    No Known Activations