© 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. 63359
    Prev
    Next
    INDEX
    Explanations

    warm temperatures and weather

    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
    /sources
    -0.08
    atable
    -0.08
    订éĺħä¸ĵæłı
    -0.08
    被åĪ«äºº
    -0.08
    .pb
    -0.08
    äºĶé¢ľåħŃèī²çļĦ
    -0.08
    è¢«æŁ¥
    -0.07
     appunto
    -0.07
    æįŁå¤±çļĦ
    -0.07
    yna
    -0.07
    POSITIVE LOGITS
     conducive
    0.07
     temperatures
    0.07
    ç»ĪæĹ¥
    0.07
    quences
    0.07
     пÑĢогÑĢе
    0.06
     summ
    0.06
    ischt
    0.06
    温æļĸ
    0.06
     conditions
    0.06
     permitting
    0.06
    Activations Density 0.058%

    No Known Activations