© 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. 38117
    Prev
    Next
    INDEX
    Explanations

    environment, technology, life, resources, disorders

    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
    è§ģäºĨ
    -0.08
    ---</
    -0.08
    estia
    -0.07
    unky
    -0.07
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.07
    oya
    -0.07
    odu
    -0.07
    fic
    -0.07
    ank
    -0.07
    ÐĿÐĺÐķ
    -0.07
    POSITIVE LOGITS
    ä¸įçĶĺå¿ĥ
    0.07
    باب
    0.07
    åĴĮ丰å¯ĮçļĦ
    0.06
     incol
    0.06
    0.06
    以åıĬåIJĦç§į
    0.06
    éļ
    0.06
    egger
    0.06
    æĸ¯åŁº
    0.06
    éĶIJæĦıè¿Ľåıĸ
    0.06
    Activations Density 0.525%

    No Known Activations