© 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. 35550
    Prev
    Next
    INDEX
    Explanations

    bed trailer

    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
    å·¢
    -0.09
    æĬĽ
    -0.09
    лÑij
    -0.09
    æĮīä¸ĭ
    -0.09
    路线
    -0.09
    ãĤ³ãĥ¼ãĤ¹
    -0.08
    æŀķ
    -0.08
    å¼łåħĪçĶŁ
    -0.08
    igue
    -0.08
    .NewLine
    -0.08
    POSITIVE LOGITS
    pmat
    0.10
    å¼ĢéŨ
    0.10
    å¡Ķ
    0.10
    æĪŁ
    0.09
    èĭ¹
    0.09
    ınd
    0.09
    åĸĤ
    0.08
    éľ²åĩº
    0.08
    ongan
    0.08
    çłģ头
    0.08
    Activations Density 0.102%

    No Known Activations