© 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. 62776
    Prev
    Next
    INDEX
    Explanations

    sadness, grief, mourning

    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
    æĭ©
    -0.10
    è²Į
    -0.10
    å´ĩæĭľ
    -0.10
    ÑĢаÐ
    -0.09
    许ä¹ħ
    -0.09
    趣
    -0.09
     GPLv
    -0.09
    åĶ¾
    -0.09
    å¾Īå¼Ģå¿ĥ
    -0.09
    å´ĩå°ļ
    -0.08
    POSITIVE LOGITS
    åĵŃ
    0.14
    æĤ²ä¼¤
    0.11
    åĵĢ
    0.11
    è°¯
    0.10
    åķ¼
    0.10
    åijľ
    0.10
    åĵŃæ³£
    0.10
    伤å¿ĥ
    0.10
    çĹĽ
    0.10
    æĤ²åĵĢ
    0.09
    Activations Density 0.050%

    No Known Activations