© 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. 56694
    Prev
    Next
    INDEX
    Explanations

    April Myers

    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
    èĦĨ
    -0.09
     Gór
    -0.09
    ACC
    -0.09
    ãĥļ
    -0.09
    æģĭ
    -0.09
    èģĶç½ij
    -0.09
    æĸĩç«łæĿ¥æºIJ
    -0.08
     Plaza
    -0.08
    ims
    -0.08
    æ´ģçĻ½
    -0.08
    POSITIVE LOGITS
    æłĩçļĦ
    0.10
    æĢ§ä»·æ¯Ķ
    0.10
    å°ĨæĿ¥
    0.10
    ä¹°åħ¥
    0.09
    å»ī
    0.09
    ä¾¿å®ľ
    0.09
    æľªæĿ¥
    0.09
    åŁºç¡Ģ设æĸ½
    0.09
    dden
    0.09
    åIJĪãģĦ
    0.09
    Activations Density 0.163%

    No Known Activations