© 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. 4038
    Prev
    Next
    INDEX
    Explanations

    Asia-Pacific region

    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
    errupt
    -0.09
    sWith
    -0.08
    ski
    -0.08
    ened
    -0.08
    ness
    -0.08
    ros
    -0.08
    iler
    -0.08
    å±±åĿ¡
    -0.08
    è¿Ľé¡¹
    -0.08
    ubo
    -0.08
    POSITIVE LOGITS
    -Pacific
    0.15
    åĵºä¹³
    0.10
    cribe
    0.10
    adero
    0.09
    åĮĸçļĦ
    0.09
    erts
    0.09
    太平æ´ĭ
    0.09
    .sleep
    0.09
    cul
    0.09
    ahead
    0.09
    Activations Density 0.015%

    No Known Activations