© 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. 16952
    Prev
    Next
    INDEX
    Explanations

    Brazil

    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
    edin
    -0.20
    oire
    -0.18
    eenth
    -0.18
    çĦ¶æĺ¯
    -0.18
     Microsystems
    -0.17
     Romney
    -0.17
    еÑĢÑĮ
    -0.17
    -handed
    -0.17
    ohana
    -0.17
    fare
    -0.16
    POSITIVE LOGITS
    0.21
    fest
    0.17
    æ£Ĵ
    0.16
    -born
    0.16
    .amazon
    0.16
    isation
    0.16
    çī¹æľīçļĦ
    0.16
    isms
    0.16
    ism
    0.16
    mega
    0.16
    Activations Density 0.009%

    No Known Activations