© 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. 10374
    Prev
    Next
    INDEX
    Explanations

    field

    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
    HV
    -0.21
    大
    -0.20
    unes
    -0.20
    æģķ
    -0.19
     socialist
    -0.19
    ä¸ĵ
    -0.19
    quin
    -0.18
    conf
    -0.18
    imore
    -0.18
    åĢ¡
    -0.18
    POSITIVE LOGITS
    çī¹åĪ«å£°æĺİ
    0.20
    çĶ¨å¾®ä¿¡
    0.20
    ì¶ķ
    0.19
    èµĿ
    0.19
    馥
    0.19
    .React
    0.19
    åĮ»ç§ij
    0.19
    åĪijäºĭæ¡Ī件
    0.18
    æıIJéĢŁ
    0.18
     |_|
    0.18
    Activations Density 0.022%

    No Known Activations