© 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. 10528
    Prev
    Next
    INDEX
    Explanations

    va<ctrl63>

    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
    æݪ
    -0.18
     Hess
    -0.17
    pmat
    -0.17
    åIJİ代
    -0.17
    ÑĭÑĪ
    -0.17
    andelier
    -0.17
    IRST
    -0.17
    å½ĵæĪIJ
    -0.17
    INGTON
    -0.16
    æĭħ
    -0.16
    POSITIVE LOGITS
    rium
    0.23
    åįĬå²Ľ
    0.19
    ium
    0.19
    çĤľ
    0.19
    è°²
    0.19
     vehement
    0.18
    çļĦä¸ĢåĪĩ
    0.18
    串èģĶ
    0.18
    é²į
    0.18
    ä¸ŃåįİæĸĩåĮĸ
    0.18
    Activations Density 0.202%

    No Known Activations