© 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. 37181
    Prev
    Next
    INDEX
    Explanations

    has/have/had + object

    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
    åIJĮæĥħ
    -0.10
     пÑĢеж
    -0.10
    çĶŁåij½çļĦ
    -0.10
    èĻ½çĦ¶æĺ¯
    -0.09
    èĥĮåIJİ
    -0.09
    åīįéĿ¢
    -0.09
    åįĪé¥Ń
    -0.09
    çļĦåĮºåĪ«
    -0.08
     cabe
    -0.08
    éªĮ
    -0.08
    POSITIVE LOGITS
    ollect
    0.09
    agal
    0.09
    æݨèįIJéĺħ读
    0.08
     inf
    0.08
    PLICATION
    0.08
     Amendments
    0.08
    .ready
    0.08
    apr
    0.08
    elman
    0.08
    æĪ·
    0.08
    Activations Density 0.126%

    No Known Activations