© 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. 10449
    Prev
    Next
    INDEX
    Explanations

    may not be

    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
     anything
    -0.21
    常æĢģ
    -0.18
     Ask
    -0.17
    ä»Ģä¹Īåij¢
    -0.17
    å¤ĸéĥ¨
    -0.17
    æīĢè°ĵ
    -0.16
    Advertisements
    -0.16
    ãģ¨ãģĦãģĪãģ°
    -0.16
    缮çļĦåľ¨äºİ
    -0.16
    ocode
    -0.16
    POSITIVE LOGITS
    çľĭæ¸ħ
    0.19
    åħ¼é¡¾
    0.19
    iona
    0.19
    çĥŃå¿ĥ
    0.19
    -know
    0.18
    èĨĽ
    0.18
    å¼ĢåıijåĮº
    0.18
    ions
    0.18
    åħ·å¤ĩ
    0.17
    rosse
    0.16
    Activations Density 0.016%

    No Known Activations