© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 47801
    Prev
    Next
    INDEX
    Explanations

    remember followed by clause

    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
    trap
    -0.10
    éĽī
    -0.09
    åĭĭç«ł
    -0.09
    æĪijçĽ¸ä¿¡
    -0.09
    èŃ°
    -0.09
    å¿«ä¸ī
    -0.08
    екÑģ
    -0.08
    æĭ¯
    -0.08
    çħ§æĸĻ
    -0.08
    ICIENT
    -0.08
    POSITIVE LOGITS
    说è¿ĩ
    0.13
     ÑĢанÑĮÑĪе
    0.11
    æĽ¾åľ¨
    0.11
    ä»ĸæĽ¾
    0.10
    ä¸Ĭ次
    0.10
    æľīç§į
    0.10
     earlier
    0.10
    ä¹ŁæĽ¾
    0.09
    æľīè¿ĩ
    0.09
    éĤ£æŶ
    0.09
    Activations Density 0.010%

    No Known Activations