© 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. 10443
    Prev
    Next
    INDEX
    Explanations

    memory foam pillowtop

    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
    -Compatible
    -0.10
    æĪ®
    -0.10
    æºħ
    -0.09
    åģľäº§
    -0.09
    å®ļå±ħ
    -0.09
    æľ½
    -0.09
    æ±ĩ
    -0.09
    wner
    -0.08
    æݺ
    -0.08
    ä¸Ģèīĺ
    -0.08
    POSITIVE LOGITS
    ighton
    0.09
     brace
    0.08
     Bam
    0.08
    åįļå¼Ī
    0.08
    åIJ¸
    0.08
     invoked
    0.08
    loss
    0.08
     Creek
    0.08
    奴
    0.08
    æĭĽçĶŁ
    0.08
    Activations Density 0.174%

    No Known Activations