© 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. 17313
    Prev
    Next
    INDEX
    Explanations

    manifestations and manifest.json

    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
    iper
    -0.24
    æ¢ħå·ŀ
    -0.17
    hammer
    -0.17
    erce
    -0.16
    æľªå¿ħ
    -0.16
    æ°´åºĵ
    -0.15
    itch
    -0.15
    ument
    -0.15
    pton
    -0.15
    ystone
    -0.15
    POSITIVE LOGITS
    edly
    0.23
    ly
    0.19
    eful
    0.19
    eners
    0.17
    æĺ¯æĪijçļĦ
    0.17
    è°ģçŁ¥éģĵ
    0.17
    们
    0.17
    ectomy
    0.16
    è°ģèĥ½
    0.16
    ness
    0.16
    Activations Density 0.021%

    No Known Activations