© 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. 19690
    Prev
    Next
    INDEX
    Explanations

    radioactive decay and activity changes

    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
     berk
    -0.08
     STRICT
    -0.08
    伸缩
    -0.08
    avat
    -0.07
     Inhalts
    -0.07
    myp
    -0.07
     privileged
    -0.07
    æĪijåĴĮä½ł
    -0.07
    omotor
    -0.07
    ãĤį
    -0.07
    POSITIVE LOGITS
     decay
    0.09
     Decay
    0.08
    è¡°
    0.08
     exponentially
    0.08
    æĢ»éĩı
    0.08
     losses
    0.08
     dwind
    0.08
     peak
    0.07
    -days
    0.07
    å³°åĢ¼
    0.07
    Activations Density 0.004%

    No Known Activations