© 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. 61828
    Prev
    Next
    INDEX
    Explanations

    playing out, unfolding, or drama occurring

    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
    æľīæīĢ
    -0.09
    nak
    -0.08
     اÙĦÙĤر
    -0.08
    .addClass
    -0.08
    qr
    -0.08
     jo
    -0.08
    帰
    -0.08
    oux
    -0.08
    hurst
    -0.08
    åŃĺåľ¨éĹ®é¢ĺ
    -0.08
    POSITIVE LOGITS
    ä¸Ĭæ¼Ķ
    0.14
     unfold
    0.13
    æ¼Ķç»İ
    0.12
     unfolding
    0.12
    ä¸Ģå¹ķ
    0.11
     unfolds
    0.10
    æĪı
    0.10
    çļĦåıijçĶŁ
    0.09
     diá»ħn
    0.09
     unfolded
    0.09
    Activations Density 0.048%

    No Known Activations