© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 56332
    Prev
    Next
    INDEX
    Explanations

    making or preparing something

    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
    çļĦæĪIJ绩
    -0.10
    èıĬ
    -0.09
    æŃª
    -0.09
    ì§Ī
    -0.09
    æīŃæĽ²
    -0.08
    rove
    -0.08
    èıĬèĬ±
    -0.08
    émon
    -0.08
     Herbal
    -0.08
    éĢĥ
    -0.08
    POSITIVE LOGITS
    åįĵ
    0.09
    anko
    0.09
    åĩij
    0.08
    gements
    0.08
    igu
    0.08
    为ä»Ģä¹Īä¸į
    0.08
    æĪĺæĸĹåĬĽ
    0.08
    iggs
    0.08
    Lane
    0.08
    prefer
    0.07
    Activations Density 0.017%

    No Known Activations