© 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. 38197
    Prev
    Next
    INDEX
    Explanations

    cost-benefit calculations

    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
    æľĪä¸ĭ
    -0.10
    æŃ£åĢ¼
    -0.10
    æľīçĽĬ
    -0.10
    åıĹçĽĬ
    -0.09
    è§ģè¯Ĩ
    -0.09
    ç»ıæµİæĬĢæľ¯
    -0.09
    bv
    -0.08
    代价
    -0.08
    arian
    -0.08
    åłµ
    -0.08
    POSITIVE LOGITS
    FTA
    0.10
    à°³
    0.09
    æĸĩçī©ä¿ĿæĬ¤
    0.09
    åĽŀåIJĪ
    0.09
    copies
    0.09
    ihad
    0.09
    ç³į
    0.09
    åĿĩåĮĢ
    0.09
    åİĨæĿ¥
    0.09
    olini
    0.08
    Activations Density 0.164%

    No Known Activations