© 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. 27380
    Prev
    Next
    INDEX
    Explanations

    with someone or 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
    estro
    -0.09
    é¾ĻéŨ
    -0.09
    .tm
    -0.09
    éĢĶå¾Ħ
    -0.08
    ORY
    -0.08
    ATURE
    -0.08
    hek
    -0.08
    ario
    -0.08
    _Master
    -0.08
    è¹²
    -0.08
    POSITIVE LOGITS
    çļĦæĥħå½¢
    0.09
    åħ¥åĽŃ
    0.09
    kn
    0.09
    çĽ¸æľº
    0.09
    (acc
    0.09
    ç«ŀæĬĢ
    0.09
    æľŁåĪĬ
    0.09
    æĢľ
    0.09
     acc
    0.09
    од
    0.09
    Activations Density 0.054%

    No Known Activations