© 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. 17277
    Prev
    Next
    INDEX
    Explanations

    mythological figures and texts

    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
    âīĤ
    -0.26
    индив
    -0.24
    ᶣ
    -0.23
    éĩıåĮĸ
    -0.23
    Ṫ
    -0.22
    á¿ij
    -0.22
    âĦ®
    -0.22
    áµĮ
    -0.22
    âī¿
    -0.21
    Ǧ
    -0.21
    POSITIVE LOGITS
    ç¾Ŀ
    0.23
    orns
    0.22
    qli
    0.21
    åĽ½çİĭ
    0.21
    .instagram
    0.21
    èĢķåľ°
    0.20
    ä¿Ŀ驾
    0.20
    yas
    0.20
    isser
    0.20
    _ly
    0.20
    Activations Density 0.047%

    No Known Activations