© 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. 10464
    Prev
    Next
    INDEX
    Explanations

    places in Poland

    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
    ATES
    -0.22
    èĹIJ
    -0.18
    fer
    -0.18
    èĮĥåĽ´åĨħ
    -0.17
    AAP
    -0.17
    -original
    -0.17
    ically
    -0.17
     Witt
    -0.17
    篦
    -0.16
    çĽ¾
    -0.16
    POSITIVE LOGITS
    zech
    0.19
    league
    0.17
     erot
    0.17
    shed
    0.17
    èĭ¡
    0.17
    pane
    0.17
    .Pos
    0.17
    endency
    0.17
    headed
    0.16
    heading
    0.16
    Activations Density 0.238%

    No Known Activations