© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21371
    Prev
    Next
    INDEX
    Explanations

    recreate or replicate

    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
    .insertBefore
    -0.09
    çķĻå®Ī
    -0.09
    blend
    -0.09
    ertext
    -0.09
    æĬĬæīĭ
    -0.09
    éĦĦ
    -0.09
    女çİĭ
    -0.09
    æ¯ĵ
    -0.08
    afil
    -0.08
    Blend
    -0.08
    POSITIVE LOGITS
    /cop
    0.10
    åĨįçİ°
    0.10
    çļĦä¹IJ趣
    0.09
    éĩįçİ°
    0.09
    éĤ£ä»½
    0.08
    åı¤åŁİ
    0.08
     reproduce
    0.08
    è¿ĺåİŁ
    0.08
    ä¸Ĭ次
    0.08
    ä¸įåĩºæĿ¥
    0.08
    Activations Density 0.044%

    No Known Activations