© 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. 16200
    Prev
    Next
    INDEX
    Explanations

    plastic compounds and containers

    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
    éĩ
    -0.07
     rusty
    -0.07
     Supern
    -0.07
    bron
    -0.06
     Bronze
    -0.06
     bronze
    -0.06
    客è§Ĥ
    -0.06
     бÑĢон
    -0.06
    åĴĮåįķä½į
    -0.06
     Liver
    -0.06
    POSITIVE LOGITS
     plastics
    0.11
     polymer
    0.11
    æĶ¹æĢ§
    0.10
    æĪIJåŀĭ
    0.10
    注å¡ij
    0.10
    å¡ijæĸĻ
    0.09
     изделий
    0.09
     molded
    0.09
     Polymer
    0.09
     resin
    0.09
    Activations Density 0.137%

    No Known Activations