© 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. 47319
    Prev
    Next
    INDEX
    Explanations

    tax and taxation

    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
    adoo
    -0.08
    lecht
    -0.07
    佳人
    -0.07
    æ³ĵ
    -0.07
    æĤĶ
    -0.07
    åĪ¹éĤ£
    -0.07
    忱
    -0.07
    лове
    -0.07
    åĩºèµ°
    -0.07
    fasta
    -0.07
    POSITIVE LOGITS
    å¾ģæĶ¶
    0.14
     taxes
    0.12
     taxation
    0.12
     taxing
    0.11
     tax
    0.11
     lev
    0.11
     levy
    0.11
    å¾ģ管
    0.11
     revenues
    0.11
    è´¢æĶ¿æĶ¶åħ¥
    0.11
    Activations Density 0.075%

    No Known Activations