© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 17150
    Prev
    Next
    INDEX
    Explanations

    numbers, prices, and divisions

    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
    Negative Logits
    ent
    -0.23
    ore
    -0.23
    ous
    -0.22
     program
    -0.21
    ese
    -0.21
    vey
    -0.21
     ever
    -0.21
    ite
    -0.20
    ”
    -0.20
    i
    -0.20
    POSITIVE LOGITS
    èī²æ³½
    0.25
     pornô
    0.24
    åĶ®ä»·
    0.23
     follando
    0.23
    çĸ¯
    0.21
    å¸Ĥåľºä»·æł¼
    0.21
    èİ«åIJį
    0.21
    è¿Ļ两天
    0.21
    éĺŁåıĭ
    0.21
     vÃŃde
    0.20
    Activations Density 0.080%

    No Known Activations