© 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. 48448
    Prev
    Next
    INDEX
    Explanations

    anniversary

    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
    hare
    -0.07
    ãĤ·ãĥ§ãĥ¼
    -0.07
    èİ·èµŀ
    -0.07
    lesi
    -0.07
    æĪIJåĬŁåIJİåį³åı¯
    -0.07
     dẹp
    -0.07
    ç¾İæĦŁ
    -0.07
    缨
    -0.06
    å¤ĩçĶ¨
    -0.06
    Singleton
    -0.06
    POSITIVE LOGITS
     anniversary
    0.10
    纪念
    0.09
    ãģ¡ãĤĩãģĨãģ©
    0.09
    ä¹ĭéĻħ
    0.09
    à¸ŀà¸Ńà¸Ķี
    0.08
     Jubil
    0.08
    à¸Ħรà¸ļ
    0.08
    èµ°è¿ĩäºĨ
    0.08
     commemor
    0.08
    ãĤĴè¿İ
    0.08
    Activations Density 0.248%

    No Known Activations