© 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. 17082
    Prev
    Next
    INDEX
    Explanations

    start of code or technical terms

    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
    以æѤ
    -0.21
     Ink
    -0.21
    edy
    -0.21
    INY
    -0.19
    ä¸Ģéĥ¨
    -0.19
     handicap
    -0.19
    ör
    -0.18
    aby
    -0.18
    åĽ¹
    -0.18
    oda
    -0.18
    POSITIVE LOGITS
    åľ°çĤ¹
    0.21
    leine
    0.20
    æĸĽ
    0.19
    æĬ¥åijĬ
    0.19
    æķ·
    0.19
    occo
    0.18
    踪
    0.18
    resolver
    0.18
    女足
    0.18
    管家
    0.18
    Activations Density 0.002%

    No Known Activations