© 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. 4742
    Prev
    Next
    INDEX
    Explanations

    names like Maria, Omar, Tamar

    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
    sWith
    -0.11
    黳
    -0.10
    nox
    -0.10
    spiel
    -0.10
    dre
    -0.10
    æŀĭ
    -0.09
    å©ļåIJİ
    -0.09
    æĦı大
    -0.09
    erman
    -0.09
    ItemAt
    -0.09
    POSITIVE LOGITS
    转载请
    0.09
    ending
    0.09
    æĿĢæīĭ
    0.09
    èĦIJ
    0.08
    idge
    0.08
    åŃĹåı·
    0.08
    usz
    0.08
    ial
    0.08
    otechn
    0.08
    ÙĤب
    0.07
    Activations Density 0.031%

    No Known Activations