© 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. 16942
    Prev
    Next
    INDEX
    Explanations

    CD changer, hardware, software, Maya, servers

    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
    Not in Any Lists

    No Comments

    Negative Logits
    _UNDEFINED
    -0.19
    stag
    -0.18
    æij©
    -0.18
    _expect
    -0.17
    xfb
    -0.17
    _strategy
    -0.17
    wg
    -0.17
    _extend
    -0.17
    ifu
    -0.17
    oron
    -0.17
    POSITIVE LOGITS
    åħ¨èµĦåŃIJ
    0.18
    æľīçĽĬ
    0.18
    太å°ij
    0.18
     omnip
    0.17
     pec
    0.17
     ÐŁÐ¾Ñĩем
    0.17
    èĬĤ
    0.17
     sublist
    0.17
     hers
    0.17
     las
    0.16
    Activations Density 3.553%

    No Known Activations