© 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. 55561
    Prev
    Next
    INDEX
    Explanations

    time to order or when time came

    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
    åīįæıIJæĺ¯
    -0.10
    æ´½
    -0.10
    æľºåĪ¶
    -0.10
    ç©·
    -0.10
    åİ»çľĭçľĭ
    -0.09
    åİŁåĽłä¹ĭä¸Ģ
    -0.09
    æļĹ示
    -0.09
    è¿Ŀ
    -0.09
     casualty
    -0.09
    为ä¸Ńå¿ĥ
    -0.09
    POSITIVE LOGITS
     instead
    0.08
    èµ·äºĨ
    0.08
    论
    0.07
    ãĤ¿ãĥ«
    0.07
    æľ¬äºº
    0.07
    sanitize
    0.07
    ä¸Ģäºĭ
    0.07
     pl
    0.07
     stuck
    0.07
     Katrina
    0.07
    Activations Density 0.025%

    No Known Activations