© 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. 14462
    Prev
    Next
    INDEX
    Explanations

    trademarks and properties

    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
    å¤ļä½ĻçļĦ
    -0.22
    空
    -0.20
    å¤ļä½Ļ
    -0.20
    æĮ½æķij
    -0.20
     post
    -0.19
    åŁ¹åħ»
    -0.19
    æĭĺ
    -0.18
     extra
    -0.18
    深度
    -0.18
    OptionsResolver
    -0.18
    POSITIVE LOGITS
    å¦Ĥæľīä¾µæĿĥ
    0.23
    åŃĹåı·
    0.23
    allen
    0.22
    åı¦è¡Į
    0.22
     trademarks
    0.21
    å°Ĭ严
    0.21
    åĨħè¡£
    0.21
    ä¾Ŀæ³ķ
    0.20
    èĩ´æķ¬
    0.20
    éĵ®
    0.20
    Activations Density 0.018%

    No Known Activations