© 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. 12835
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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
    缸åĬ©
    -0.21
    bnb
    -0.18
    .ro
    -0.17
    ahan
    -0.17
    план
    -0.17
    éĤ£å°±
    -0.16
     taraf
    -0.16
     prin
    -0.16
    åħ³éĶ®æŶåĪ»
    -0.16
    gens
    -0.16
    POSITIVE LOGITS
    æľ¬æĿ¥
    0.25
    ãģ¨ãģĦãģĪãģ°
    0.24
    à¹Ģà¸Ńà¸ĩ
    0.23
    çļĦ好å¤Ħ
    0.23
    åIJĮæĹ¶ä¹Łæĺ¯
    0.23
    ä¹ŁæĪIJ为
    0.23
    çĶļèĩ³è¿ĺ
    0.22
    æľ¬èº«
    0.22
    ä¸įä½Ĩ
    0.22
     vá»ijn
    0.21
    Activations Density 0.114%

    No Known Activations