© 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. 10516
    Prev
    Next
    INDEX
    Explanations

    explaining difficulty capturing or describing

    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
    изаÑĨии
    -0.23
    æįIJ
    -0.22
    çĶ
    -0.22
    èĢ¿
    -0.21
    atat
    -0.21
    åijĹ
    -0.20
    åİ»åĵªéĩĮ
    -0.18
    âĢ½
    -0.18
    æĹłäºº
    -0.18
    磮
    -0.18
    POSITIVE LOGITS
    æĴ·
    0.26
     infra
    0.22
    ä¼ł
    0.21
    综åIJĪ
    0.21
    ç»Ļä½łä»¬
    0.20
    ç»Ļ人
    0.20
    ä¸į失
    0.19
    infra
    0.19
     combined
    0.19
    ç²Ĺç³Ļ
    0.18
    Activations Density 0.022%

    No Known Activations