© 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. 40006
    Prev
    Next
    INDEX
    Explanations

    refrigerate, refrigerator, fridge

    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
    ipse
    -0.08
    å¸Ī表
    -0.07
    ç¦
    -0.07
    æĻĴ太éĺ³
    -0.07
    éĢłèĪ¹
    -0.07
     Fires
    -0.07
     Surya
    -0.07
    çīµ
    -0.07
    æĪ¿å¤©ä¸ĭ
    -0.07
     رسÙħ
    -0.07
    POSITIVE LOGITS
    åĨ·èĹı
    0.12
     refriger
    0.11
    åĨ·éĵ¾
    0.11
    åĪ¶åĨ·
    0.10
     ÑħолодилÑĮ
    0.10
    ä½İ温
    0.10
    åĨ·åį´
    0.09
    åĨ°
    0.09
     Refriger
    0.09
     cooler
    0.09
    Activations Density 0.024%

    No Known Activations