© 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. 11869
    Prev
    Next
    INDEX
    Explanations

    regardless, even, despite

    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
    fits
    -0.08
    ä½Ĩä»İ
    -0.08
    横
    -0.08
    åIJ¦è®¤
    -0.08
    éĽī
    -0.08
    羣æŃ£çļĦ
    -0.08
    æ¯
    -0.08
    ale
    -0.08
    äºĽä»Ģä¹Ī
    -0.08
    enet
    -0.07
    POSITIVE LOGITS
    åĵªæĢķæĺ¯
    0.16
    åĵªæĢķ
    0.15
     ê·¸ê²ĥ
    0.11
    åį³ä½¿
    0.10
    å®ĥåı¯ä»¥
    0.10
    æĺİçŁ¥
    0.09
    å°±ç®Ĺæĺ¯
    0.09
    åĨįè§ģ
    0.09
    çķļ
    0.09
    ç§ģ人
    0.09
    Activations Density 0.042%

    No Known Activations