© 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. 10661
    Prev
    Next
    INDEX
    Explanations

    introduction "The"

    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
    owed
    -0.19
    èѬ
    -0.19
     trick
    -0.19
    atre
    -0.19
    utral
    -0.18
    OMB
    -0.18
    alog
    -0.18
    Allen
    -0.18
    urent
    -0.18
    alyzer
    -0.18
    POSITIVE LOGITS
     пÑĥнк
    0.21
    æµ´
    0.21
     Mills
    0.19
    åħ±è®¡
    0.19
    袪
    0.19
    è¯Ŀé¢ĺ
    0.19
    GOR
    0.19
    æŃ£æĸĩ
    0.19
    nge
    0.18
    KER
    0.18
    Activations Density 0.030%

    No Known Activations