© 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. 10556
    Prev
    Next
    INDEX
    Explanations

    medium heat or Q:

    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
    éļĶ
    -0.22
    æ´Ĺ
    -0.20
    æĬĽ
    -0.19
    onet
    -0.18
     perfectly
    -0.18
     Wich
    -0.18
    ully
    -0.18
    æ´ĹåĩĢ
    -0.18
    åī²
    -0.18
    alist
    -0.18
    POSITIVE LOGITS
    éĢļé£İ
    0.22
     thÆ°Æ¡ng
    0.20
    REA
    0.19
    _coverage
    0.19
     пÑĢог
    0.18
    à¹Ħà¸ĭ
    0.18
    ﹤
    0.18
    ÑģÑĤанов
    0.17
    utral
    0.17
    utr
    0.17
    Activations Density 0.007%

    No Known Activations