© 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. 16761
    Prev
    Next
    INDEX
    Explanations

    Saturday Night Live, New Yorker

    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
    eur
    -0.19
     Quarter
    -0.18
     unp
    -0.18
    é»ij马
    -0.18
    media
    -0.17
    çĥŃçĤ¹
    -0.17
    Infinity
    -0.17
    å·´æĸ¯
    -0.17
    éļ¾è¿ĩ
    -0.17
    å¹²èĦĨ
    -0.17
    POSITIVE LOGITS
    ä¿¡èµĸ
    0.21
    .microsoft
    0.20
    ìĽĥ
    0.19
    ENN
    0.19
    éĥĬ
    0.18
    ç»ıåİĨ
    0.18
    æīĵæĭ¼
    0.18
    éĹ³
    0.18
     vet
    0.17
    åıijå±ķè§ĦåĪĴ
    0.17
    Activations Density 0.002%

    No Known Activations