© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2278
    Prev
    Next
    INDEX
    Explanations

    renewable energy generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
     themes
    -0.27
     genres
    -0.26
    Hierarchy
    -0.26
     genre
    -0.25
    å©´
    -0.25
    æĭĺ
    -0.25
    _plain
    -0.25
     Genre
    -0.24
    /themes
    -0.24
     endings
    -0.24
    POSITIVE LOGITS
    åħīä¼ı
    0.54
    太éĺ³èĥ½
    0.54
     solar
    0.50
    åħīä¼ıåıijçĶµ
    0.47
     rooftop
    0.45
    é£İçĶµ
    0.44
     retrofit
    0.43
    Solar
    0.43
    åĤ¨èĥ½
    0.40
    ovolta
    0.40
    Activations Density 0.052%

    No Known Activations