© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7788
    Prev
    Next
    INDEX
    Explanations

    duration or end point

    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
    çķĻä¸ĭ
    -0.10
    åģľçķĻåľ¨
    -0.10
    éĢŁ
    -0.10
    æĤ¬æµ®
    -0.10
     knot
    -0.09
    çį¬
    -0.09
    åħķ
    -0.09
    isting
    -0.09
    /sys
    -0.09
    缴åįĩ
    -0.09
    POSITIVE LOGITS
    uren
    0.11
    rait
    0.08
    æ·ĺ
    0.08
     eternity
    0.08
    ç³ľ
    0.08
    å½ĵä¹ĭæĹłæĦ§
    0.08
    æķ´ä¸ª
    0.08
    éĹº
    0.08
    ç²Ĵ
    0.08
     concert
    0.08
    Activations Density 0.012%

    No Known Activations