© 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. 10354
    Prev
    Next
    INDEX
    Explanations

    Open Championship

    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
    æ¼ĵ
    -0.21
     Horde
    -0.21
    æ¹Ħ
    -0.19
    ssi
    -0.19
    ollipop
    -0.18
    .dismiss
    -0.18
     assort
    -0.18
    è¿Ľåİ»
    -0.18
    elog
    -0.17
     clipped
    -0.17
    POSITIVE LOGITS
    åĿĬ
    0.19
    _PRINTF
    0.18
    åĴĦ
    0.18
    çĦ¦
    0.18
    éĵºè®¾
    0.18
    æĭĻ
    0.18
    spath
    0.18
     weekend
    0.18
    åij¨æľ«
    0.18
    æ¡Ģ
    0.17
    Activations Density 0.003%

    No Known Activations