© 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. 9071
    Prev
    Next
    INDEX
    Explanations

    best results

    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
    ä»£æĽ¿
    -0.09
    ç»Ī身
    -0.09
    æĽ¿ä»£
    -0.09
    -collapse
    -0.09
    ëĭ¹
    -0.09
    åĽ±
    -0.09
    访
    -0.08
    嵯
    -0.08
    å¿į
    -0.08
    APT
    -0.08
    POSITIVE LOGITS
    æľĢä½³
    0.24
     best
    0.22
    æľĢ好
    0.22
    æľĢ好çļĦ
    0.21
    çļĦæľĢä½³
    0.20
    æľĢéĢĤåIJĪ
    0.18
    .best
    0.18
    æľĢ好æĺ¯
    0.18
    best
    0.18
    Best
    0.17
    Activations Density 0.123%

    No Known Activations