© 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. 10373
    Prev
    Next
    INDEX
    Explanations

    early, first, fast, longer, rate

    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
    -contrib
    -0.21
    åIJĪæ³ķæĢ§
    -0.20
    ãĥĻãĤ¹ãĥĪ
    -0.19
    æľīå¤ļ大
    -0.19
    çĥ§
    -0.19
    æŃ£å½ĵ
    -0.19
    å·§åIJĪ
    -0.18
    èİħ
    -0.18
    大å¹ħæıIJåįĩ
    -0.18
    terr
    -0.18
    POSITIVE LOGITS
    åħĪè¡Į
    0.36
    çİĩåħĪ
    0.35
    èµ°åľ¨
    0.26
     privileged
    0.23
     compared
    0.22
    -relative
    0.22
    åįķçĭ¬
    0.22
    privileged
    0.22
     ahead
    0.22
    ä¸ĢèĪ¬äºº
    0.22
    Activations Density 0.217%

    No Known Activations