© 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. 23707
    Prev
    Next
    INDEX
    Explanations

    African country capitals

    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
    éĩįè¦ģæĦıä¹ī
    -0.10
    æĺĢ
    -0.09
    éĹ´æİ¥
    -0.09
    çĶľçĶľ
    -0.09
    å¿«æĿ¥
    -0.09
    çĶŁçIJĨ
    -0.09
    ç®Ģ便
    -0.09
    stown
    -0.08
    åŀ¦
    -0.08
    å¿«ä¸ī
    -0.08
    POSITIVE LOGITS
    createElement
    0.09
    æĢ»çIJĨ
    0.08
    stem
    0.08
    asket
    0.08
    ä¸įå®ļ
    0.08
    åı¯è¡Į
    0.08
    itation
    0.08
    èµŀèµı
    0.08
    æľīåħ³éĥ¨éŨ
    0.08
    /provider
    0.08
    Activations Density 0.068%

    No Known Activations