© 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. 10574
    Prev
    Next
    INDEX
    Explanations

    disabled/enabled status

    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
    åŃļ
    -0.23
    è´°
    -0.18
    elts
    -0.18
    _OLD
    -0.18
    imed
    -0.18
    edor
    -0.18
    âŀ£
    -0.18
    phe
    -0.18
     OLD
    -0.17
    çĦ¶
    -0.17
    POSITIVE LOGITS
    /import
    0.21
    ä¸Ģçīĩ
    0.20
    æŀ§
    0.20
    çļĦæĦŁåıĹ
    0.20
     exem
    0.19
    çĶ°éĩİ
    0.18
    æĦŁåıĹ
    0.18
    nation
    0.18
    ilk
    0.18
    ynn
    0.18
    Activations Density 0.004%

    No Known Activations