© 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. 10386
    Prev
    Next
    INDEX
    Explanations

    commentary and interpretation

    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
    ocha
    -0.20
    Licensed
    -0.19
    ment
    -0.19
    éĹ²
    -0.18
     Stick
    -0.18
    æ©Ľ
    -0.18
    èĥ´
    -0.18
    pawn
    -0.18
    .gif
    -0.18
    aw
    -0.18
    POSITIVE LOGITS
    解读
    0.24
    éĺIJéĩĬ
    0.24
    解éĩĬ
    0.23
     interpretations
    0.22
     interpretation
    0.21
     commentary
    0.20
    èľ¡
    0.20
    课æĸĩ
    0.20
     Commentary
    0.20
    ä¸įåĪ°ä½į
    0.20
    Activations Density 0.025%

    No Known Activations