© 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. 20419
    Prev
    Next
    INDEX
    Explanations

    ecosystem services and ecology

    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
    fg
    -0.06
    ortal
    -0.05
    çªĺ
    -0.05
    brigen
    -0.05
    å¼Ģæĭĵè¿Ľåıĸ
    -0.05
    à¹Ģหลืà¸Ń
    -0.05
     detect
    -0.05
    åı¯æĥľ
    -0.05
    æĪIJ群
    -0.05
     patch
    -0.05
    POSITIVE LOGITS
     balancing
    0.07
    -bal
    0.06
    åĴĮç»´æĬ¤
    0.06
     balanced
    0.06
    astro
    0.06
    balanced
    0.06
     balances
    0.06
    OLI
    0.06
    illion
    0.06
    è®
    0.06
    Activations Density 0.010%

    No Known Activations