© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 28038
    Prev
    Next
    INDEX
    Explanations

    thanks and acknowledgement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    çĶļ
    -0.09
     vest
    -0.08
    åī¯ç§ĺ书éķ¿
    -0.08
    ç»ĥä¹ł
    -0.08
    ç¼Ģ
    -0.08
    âĤį
    -0.08
    æĸ¹å¼ıè¿Ľè¡Į
    -0.08
    娱ä¹IJ
    -0.08
     Dare
    -0.08
    åĥµ
    -0.08
    POSITIVE LOGITS
    æĦŁè°¢
    0.14
     thanks
    0.13
    表æī¬
    0.10
    å¹ķåIJİ
    0.10
    æĦŁè¬Ŀ
    0.10
    谢谢
    0.10
     Thanks
    0.10
    -parser
    0.09
    Thanks
    0.09
    å°¤
    0.09
    Activations Density 0.033%

    No Known Activations