© 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. 10685
    Prev
    Next
    INDEX
    Explanations

    captivatingly gripping entertainment

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Ware
    -0.20
    WARE
    -0.19
     salopes
    -0.18
    icl
    -0.18
     ÐIJлекÑģан
    -0.18
     joke
    -0.18
    iversary
    -0.17
    vider
    -0.17
    ificate
    -0.17
     pil
    -0.17
    POSITIVE LOGITS
    ä½ıäºĨ
    0.27
    注æĦıåĬĽ
    0.24
    ä¸įèĪį
    0.24
    ä¸įä½ı
    0.23
     attention
    0.21
    çľ¼çIJĥ
    0.21
    ingly
    0.20
    æĻĤéĸĵãģĮ
    0.20
    çĦ¼ãģį
    0.20
     audiences
    0.19
    Activations Density 0.009%

    No Known Activations