© 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. 13544
    Prev
    Next
    INDEX
    Explanations

    interest rates, prices, current time

    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
    åľ°éģĵ
    -0.20
    неÑĨ
    -0.19
    å¼ĢåĪĽ
    -0.19
    éĥ¨èIJ½
    -0.18
     incr
    -0.18
    æ®ĭ
    -0.18
    ç³»ç»ŁçļĦ
    -0.18
     residual
    -0.18
     Battles
    -0.18
     terrain
    -0.17
    POSITIVE LOGITS
    æĪijå½ĵæŶ
    0.23
    åħ¬å¸ĥçļĦ
    0.23
    å½ĵæŶçļĦ
    0.23
    æ³¢åĬ¨
    0.23
     prices
    0.23
    éĤ£å¤©
    0.23
    åıĺåĬ¨
    0.22
    çī©ä»·
    0.22
    åıĺåĮĸ
    0.22
    å½ĵæĹ¥
    0.22
    Activations Density 0.029%

    No Known Activations