© 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. 10526
    Prev
    Next
    INDEX
    Explanations

    California Air Control Board

    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
    جÙĨ
    -0.21
    .micro
    -0.20
    èĪį
    -0.19
    轸
    -0.19
    aret
    -0.19
    CharCode
    -0.19
    elts
    -0.19
    失踪
    -0.18
    enson
    -0.18
    .setFocus
    -0.18
    POSITIVE LOGITS
    æĿĤ
    0.21
    åħ¼å®¹
    0.20
    éĥ½çŁ¥éģĵ
    0.20
    èķĥ
    0.20
    鼾
    0.20
    è¿Ļ两天
    0.20
    -Compatible
    0.19
    odate
    0.19
    æĹłæīĢ
    0.19
    SG
    0.19
    Activations Density 0.005%

    No Known Activations