© 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. 17303
    Prev
    Next
    INDEX
    Explanations

    place names and identities

    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
     stem
    -0.22
     start
    -0.20
     div
    -0.20
    éĩį
    -0.20
     pron
    -0.20
    æĺ¾
    -0.19
    æĦı
    -0.19
    OUT
    -0.19
    èģĮ
    -0.19
    æĥ¶
    -0.19
    POSITIVE LOGITS
    atform
    0.26
    ataire
    0.23
    ftype
    0.21
    onian
    0.21
    楮
    0.20
    entialAction
    0.20
    inic
    0.20
    åĿŀ
    0.20
    éĻ¢éĻ¢éķ¿
    0.19
    okino
    0.19
    Activations Density 0.221%

    No Known Activations