© 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. 11909
    Prev
    Next
    INDEX
    Explanations

    economic development, business, industry

    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
    ç³Ĭ
    -0.21
    ç»Ħç»ĩçĶŁæ´»
    -0.20
    è¦ģçĤ¹
    -0.20
    leccion
    -0.20
    çºłæŃ£
    -0.20
    æ¯Ļ
    -0.19
    åħ¬å¼Ģåıij
    -0.19
    èĢ³è¾¹
    -0.19
    Combo
    -0.19
    åģıå·®
    -0.19
    POSITIVE LOGITS
    èIJ½æĪ·
    0.32
    å¼ķè¿Ľ
    0.24
    åħ¥é©»
    0.24
     кÑĢÑĥп
    0.23
     ÑģоÑģед
    0.23
    éĤ»
    0.22
     visitor
    0.22
     influx
    0.21
    è¿Ľé©»
    0.21
    èIJ½åľ°
    0.21
    Activations Density 0.097%

    No Known Activations