© 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. 17186
    Prev
    Next
    INDEX
    Explanations

    Spearheads or Spearman

    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
    OrCreate
    -0.17
     تعاÙĦÙī
    -0.17
    rogen
    -0.16
    ¡
    -0.16
    spiel
    -0.15
    ä¸įå¿ĺ
    -0.15
    tion
    -0.15
    rition
    -0.15
    uator
    -0.15
    orum
    -0.15
    POSITIVE LOGITS
    ãģĹãģı
    0.21
     Ñģобой
    0.20
    holders
    0.18
    er
    0.18
    ussen
    0.17
    ðŁı»
    0.17
     Bris
    0.16
    æĪ¬
    0.16
    zig
    0.16
    .ls
    0.16
    Activations Density 0.011%

    No Known Activations