© 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. 1688
    Prev
    Next
    INDEX
    Explanations

    activities and tasks

    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
     Handy
    -0.10
    ä¹ĭå¤Ħ
    -0.09
    ä»»ä½ķæŶåĢĻ
    -0.09
    SES
    -0.09
    alsy
    -0.08
    æį®æѤ
    -0.08
    åħ¥æīĭ
    -0.08
     consequ
    -0.08
    rades
    -0.08
     hottest
    -0.08
    POSITIVE LOGITS
    å¥ļ
    0.10
    åİĺ
    0.09
    æŀIJ
    0.09
    æĬ¤
    0.09
    究
    0.09
    好åIJĹ
    0.09
    çľģæĶ¿åºľ
    0.09
    å²ģæľĪ
    0.08
    åİ®
    0.08
    åģľäº§
    0.08
    Activations Density 0.031%

    No Known Activations