© 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. 17306
    Prev
    Next
    INDEX
    Explanations

    IN UNITED STATES

    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
    ÑĪиб
    -0.19
    主æµģ
    -0.19
    os
    -0.18
    imo
    -0.18
    _peak
    -0.17
    mal
    -0.17
    Cou
    -0.17
    åĨ¥
    -0.17
    ormal
    -0.17
    contin
    -0.17
    POSITIVE LOGITS
    çĽĤ
    0.19
    idata
    0.19
    导读
    0.19
     HERO
    0.19
    -Version
    0.18
     Implements
    0.18
    /WebAPI
    0.18
     #+#
    0.18
    NotFoundError
    0.18
    .IsNull
    0.18
    Activations Density 0.773%

    No Known Activations