© 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. 53190
    Prev
    Next
    INDEX
    Explanations

    Saturday Night Live

    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
    稽
    -0.10
     Pes
    -0.09
    inous
    -0.08
    éĢ¦
    -0.08
     Humph
    -0.08
    èĥ½ä½¿
    -0.08
    æ¸ħåĩĢ
    -0.08
    ä¹İ
    -0.08
    æĬ¤èº«
    -0.08
    cci
    -0.08
    POSITIVE LOGITS
    éĺħ读åħ¨æĸĩ
    0.11
    éºĵ
    0.09
    ãģ£ãģ¨
    0.09
    ä¸Ģæłĭ
    0.09
    è¿ĩçļĦ
    0.08
    æ¯Ĥ
    0.08
    å¸Ŀ
    0.08
    é¼ĵ
    0.08
    èĭ·
    0.08
    imon
    0.08
    Activations Density 0.002%

    No Known Activations