© 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. 52558
    Prev
    Next
    INDEX
    Explanations

    be like, be a, be in

    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
    åıŁ
    -0.09
    extends
    -0.09
    alli
    -0.09
    æŃ¤äºº
    -0.08
    女çĶŁ
    -0.08
    uisine
    -0.08
     chá
    -0.08
    chart
    -0.08
    èĮ«
    -0.08
     Pru
    -0.08
    POSITIVE LOGITS
    æݾ
    0.10
    å½ĵåģļ
    0.09
    æĪIJ为ä¸Ģ个
    0.09
     ÑĥвеÑĢ
    0.09
    éĴī
    0.09
    âĶĮ
    0.09
    ä¸Ģä½ĵåĮĸ
    0.09
    宽容
    0.09
     ÑĥвеÑĢен
    0.09
    InSection
    0.09
    Activations Density 0.084%

    No Known Activations