© 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. 56381
    Prev
    Next
    INDEX
    Explanations

    plastic waste and pollution

    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
    ļľ
    -0.08
     Shield
    -0.07
     Sheep
    -0.07
    åı°åĮº
    -0.06
    ential
    -0.06
     relocated
    -0.06
    æķĻåŃ¦æ°´å¹³
    -0.06
    eron
    -0.06
    ellow
    -0.06
     internals
    -0.06
    POSITIVE LOGITS
    çݯä¿ĿæĦıè¯Ĩ
    0.11
    åĽŀæĶ¶
    0.11
     recycl
    0.10
     recycling
    0.10
     Recycling
    0.10
    Reuse
    0.09
    ä»İæĪijåģļèµ·
    0.09
     recycle
    0.09
     waste
    0.09
    ç¢İ
    0.09
    Activations Density 0.070%

    No Known Activations