© 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. 10428
    Prev
    Next
    INDEX
    Explanations

    unwanted things

    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
    åķĸ
    -0.19
    ãĤıãģĭãĤĭ
    -0.18
    èĢĥãģĪãĤĭ
    -0.18
    walker
    -0.18
    ä½łåºĶ该
    -0.18
    ä½
    -0.18
    âľį
    -0.17
    ured
    -0.17
    ä¸į足以
    -0.17
     respective
    -0.17
    POSITIVE LOGITS
    chte
    0.21
    èĮ¬
    0.20
     surprises
    0.19
    å·²ä¹ħçļĦ
    0.19
    æŶéĹ´åĨħ
    0.17
    æľīä»»ä½ķ
    0.17
     pregnancies
    0.17
    omic
    0.17
    èĬ±æľµ
    0.17
    害
    0.17
    Activations Density 0.019%

    No Known Activations