© 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. 9539
    Prev
    Next
    INDEX
    Explanations

    neutrino oscillation or sweeney

    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
    åıijçĶŁçģ«çģ¾
    -0.08
    iones
    -0.07
     ÙĪاÙĦÙħØŃ
    -0.07
    alex
    -0.07
    çĢļ
    -0.07
    ç²¾è¯ļ
    -0.07
    åĬ³ä¿Ŀ
    -0.07
    çķĶ
    -0.07
    zik
    -0.07
    ìļķ
    -0.07
    POSITIVE LOGITS
    大åĮħ
    0.07
    ç«Ļç«Ļ
    0.07
    weeney
    0.06
    èĥĮè´Ł
    0.06
     subgroup
    0.06
     slowed
    0.06
    azon
    0.06
    åĬłéĢŁ
    0.06
     slow
    0.06
    ç³ķ
    0.06
    Activations Density 0.002%

    No Known Activations