© 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. 27910
    Prev
    Next
    INDEX
    Explanations

    will be

    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
    rams
    -0.10
     knock
    -0.09
    åĿij
    -0.09
    æ·Ģ
    -0.09
    Aligned
    -0.08
    ç»´å°Ķ
    -0.08
    æıIJåīį
    -0.08
     Ville
    -0.08
    neys
    -0.08
     Armen
    -0.08
    POSITIVE LOGITS
    æİ¥ä¸ĭæĿ¥
    0.11
    ä»ĬåIJİ
    0.11
    ãģĵãĤĮãģĭãĤī
    0.11
    æĹ¥åIJİ
    0.11
     ÑģкоÑĢо
    0.10
    好好
    0.10
     вли
    0.10
    å¾ĢåIJİ
    0.09
    erÃł
    0.09
    继ç»Ń
    0.09
    Activations Density 0.122%

    No Known Activations