© 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. 15473
    Prev
    Next
    INDEX
    Explanations

    gas, electricity, water, utility infrastructure damage

    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
     Petro
    -0.20
    aptured
    -0.20
     gab
    -0.19
    éģį
    -0.19
     Lore
    -0.18
    åıª
    -0.18
    åĵĮ
    -0.18
    ç¿ĺ
    -0.18
    çĪĩ
    -0.17
     Rin
    -0.17
    POSITIVE LOGITS
    วาà¸ĩ
    0.20
    水管
    0.20
    å·¥ä½ľèĢħ
    0.19
    ç³»ç»ŁçļĦ
    0.19
    éĥ¨éĸĢ
    0.19
     trunk
    0.18
    ksz
    0.18
    itage
    0.18
    éļĶçĥŃ
    0.18
    è¿ĽåŁİ
    0.18
    Activations Density 0.036%

    No Known Activations