© 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. 17215
    Prev
    Next
    INDEX
    Explanations

    exceptional quality

    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
    ings
    -0.19
    åŁ
    -0.17
    ÅĤem
    -0.17
    akan
    -0.17
    iming
    -0.17
     ÑģамÑĭе
    -0.16
    zilla
    -0.16
     Humph
    -0.16
    ners
    -0.16
    nder
    -0.16
    POSITIVE LOGITS
    ness
    0.27
    iveness
    0.19
    -looking
    0.18
    ity
    0.17
    ment
    0.17
    ties
    0.17
    IOR
    0.16
    uria
    0.16
     جدا
    0.16
    lü
    0.16
    Activations Density 0.015%

    No Known Activations