© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 13466
    Prev
    Next
    INDEX
    Explanations

    day or week announcements

    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
    ä¸Ģå¿ĥ
    -0.19
    ilog
    -0.18
     unity
    -0.17
    ãģ§ãģ®
    -0.17
    åŃĺåľ¨äºİ
    -0.17
     Manga
    -0.17
    ä¸Ģ大æī¹
    -0.17
    xis
    -0.17
    å¤ļåľ°
    -0.17
    èIJĮ
    -0.16
    POSITIVE LOGITS
    алÑĮн
    0.19
     Ñģобой
    0.18
    åħ¬å¹³
    0.17
    imit
    0.17
    æĪ·ç±į
    0.17
    enance
    0.17
    awning
    0.17
    çĪ
    0.17
    主è§Ĵ
    0.17
     اÙĦÙĪاØŃد
    0.17
    Activations Density 0.004%

    No Known Activations