© 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. 57209
    Prev
    Next
    INDEX
    Explanations

    Christmas day

    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
     кÑĢай
    -0.10
    æĮ¯åħ´
    -0.09
    é¦ĸåĪĽ
    -0.09
    西æ¹ĸ
    -0.09
     GD
    -0.09
    åħļæĢ»
    -0.09
     eventual
    -0.09
    ihan
    -0.09
    ót
    -0.08
    uis
    -0.08
    POSITIVE LOGITS
    åīįå¤ķ
    0.10
    اخ
    0.10
    olk
    0.09
    æł¸æ¡ĥ
    0.09
    è¿ĩåIJİ
    0.09
    æĶ»åĬ¿
    0.09
    æľŁéĹ´
    0.09
    паÑĤ
    0.08
    å®Ŀå®ī
    0.08
    åīį
    0.08
    Activations Density 0.017%

    No Known Activations