© 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. 63706
    Prev
    Next
    INDEX
    Explanations

    table related terms

    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
    ingly
    -0.10
    pery
    -0.10
    ement
    -0.09
    nable
    -0.09
    liner
    -0.09
    ../
    -0.09
    -looking
    -0.09
    åĸı
    -0.09
    opsy
    -0.09
    nels
    -0.09
    POSITIVE LOGITS
    cloth
    0.15
     اÙĦزÙħÙĨ
    0.11
    dit
    0.10
    ä¸ĬçļĦ
    0.10
    mates
    0.09
    اصر
    0.09
    unch
    0.09
    mate
    0.09
    .argsort
    0.09
    çĺ¾
    0.09
    Activations Density 0.068%

    No Known Activations