© 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. 10510
    Prev
    Next
    INDEX
    Explanations

    month day, year

    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
    Wo
    -0.18
    .mozilla
    -0.17
    zej
    -0.16
    krit
    -0.16
    worthy
    -0.16
    oust
    -0.16
    bro
    -0.16
    士
    -0.15
    cing
    -0.15
    ourg
    -0.15
    POSITIVE LOGITS
    ened
    0.20
    acker
    0.19
    ingly
    0.19
    鬧
    0.18
    ness
    0.17
    山寨
    0.16
    ç¼Ļ
    0.16
    ãģ¶ãĤĬ
    0.16
    infeld
    0.16
    èĪ·
    0.16
    Activations Density 0.016%

    No Known Activations