© 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. 10308
    Prev
    Next
    INDEX
    Explanations

    five, others, specific quantities

    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
    æķ´ä¸ªäºº
    -0.11
    amel
    -0.10
    aldo
    -0.09
     вал
    -0.09
    :`~
    -0.09
    æľīç§į
    -0.09
     custody
    -0.09
    _kw
    -0.08
     retros
    -0.08
    банк
    -0.08
    POSITIVE LOGITS
    让æ¶Īè´¹èĢħ
    0.12
     Consumer
    0.12
    æ¶Īè´¹èĢħ
    0.12
    Consumer
    0.11
    æĢ§èĥ½
    0.11
    æµĭè¯Ħ
    0.10
    æ¿Ģèµ·
    0.10
     Consumers
    0.10
    æĴĦ
    0.09
    æ¶Īè´¹èĢħçļĦ
    0.09
    Activations Density 0.100%

    No Known Activations