© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18417
    Prev
    Next
    INDEX
    Explanations

    carbon tax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    assi
    -0.06
     hab
    -0.06
     kam
    -0.05
    ãĥĨãĥ¼
    -0.05
    onia
    -0.05
     patron
    -0.05
     Pivot
    -0.05
    AGMA
    -0.05
    aglia
    -0.05
    arda
    -0.05
    POSITIVE LOGITS
    loon
    0.06
     compens
    0.06
     created
    0.06
    åĸĦ
    0.05
     participant
    0.05
    åħijçİ°
    0.05
    æµģæĶ¾
    0.05
    à¹ģà¸Ń
    0.05
    ÑĢан
    0.05
     generated
    0.05
    Activations Density 0.014%

    No Known Activations