© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21086
    Prev
    Next
    INDEX
    Explanations

    seek summit secured

    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
    åѦä½į
    -0.09
    èĤ¤
    -0.09
    æ¼ķ
    -0.09
    æĸ°åĮº
    -0.09
    à¸Ħะ
    -0.08
    allery
    -0.08
    åĢĴåľ¨
    -0.08
    沿海
    -0.08
    æľºåħ³
    -0.08
    éĽķ
    -0.08
    POSITIVE LOGITS
     Berkshire
    0.11
    åľª
    0.10
    ç½ķ
    0.09
    åĻİ
    0.09
    èĨĪ
    0.09
     famously
    0.09
    èĬĴ
    0.09
    _extractor
    0.08
    ãĤı
    0.08
     bus
    0.08
    Activations Density 0.019%

    No Known Activations