© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 11406
    Prev
    Next
    INDEX
    Explanations

    biofuels and energy production

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    害
    -0.19
    æ¡Ĩ
    -0.18
    çıIJ
    -0.18
    odium
    -0.18
    oning
    -0.18
    odox
    -0.17
    Licensed
    -0.17
    强åĬĽ
    -0.17
    åºķä¸ĭ
    -0.17
    æľĢå¤ļçļĦ
    -0.17
    POSITIVE LOGITS
    çĩĥæĸĻ
    0.32
    fuel
    0.23
     fuels
    0.21
     fuel
    0.21
    èĪĤ
    0.21
    æ¡ł
    0.20
    çĵ¢
    0.19
    æĶ¯çº¿
    0.19
     martin
    0.18
    Earlier
    0.18
    Activations Density 0.014%

    No Known Activations