© 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. 9089
    Prev
    Next
    INDEX
    Explanations

    Peyton, epitope, epitrochoid

    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
    ç¢į
    -0.11
    éĶ¢
    -0.10
    讳
    -0.10
    erva
    -0.09
    gings
    -0.09
    erv
    -0.09
    olated
    -0.09
    éĴľ
    -0.08
    ories
    -0.08
    è´¹çİĩ
    -0.08
    POSITIVE LOGITS
    sville
    0.09
    èĴľ
    0.09
     blush
    0.08
    icity
    0.08
     mee
    0.08
    å¼ķ
    0.08
    åĬªåĬĽ
    0.08
    ä½ļ
    0.08
    ran
    0.08
     Broadcasting
    0.08
    Activations Density 0.003%

    No Known Activations