© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 8958
    Prev
    Next
    INDEX
    Explanations

    neutrino oscillation

    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
    é¥
    -0.08
    åįģåħ¨
    -0.07
    ogn
    -0.07
    æĶ¹éĿ©
    -0.06
     eclectic
    -0.06
    qli
    -0.06
    åįĩéĻį
    -0.06
    гне
    -0.06
     Verg
    -0.06
     bid
    -0.06
    POSITIVE LOGITS
    /Runtime
    0.09
    寿åij½
    0.09
    è¡°
    0.09
    Lifetime
    0.08
     lifetime
    0.08
    .timeout
    0.08
    decay
    0.08
    åŃĺæ´»
    0.08
     trajet
    0.08
     decay
    0.08
    Activations Density 0.007%

    No Known Activations