© 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. 18527
    Prev
    Next
    INDEX
    Explanations

    height and weight measurements

    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
    PIO
    -0.10
    æ¶Ī
    -0.10
    çī¹æĸ¯
    -0.09
    ä¾Ľç»Ļ
    -0.09
    avage
    -0.09
    çĬ¯
    -0.09
    æĢģ
    -0.09
     pierced
    -0.09
    两家
    -0.09
     totalPages
    -0.09
    POSITIVE LOGITS
    åĬŀ好
    0.09
    æĪIJå°±æĦŁ
    0.09
    ä¸īåĨľ
    0.08
    bor
    0.08
    GraphNode
    0.08
    åĦ¿
    0.08
    uate
    0.08
    åŁİåİ¿
    0.08
    elman
    0.08
    è¾¾ä¸įåĪ°
    0.08
    Activations Density 0.005%

    No Known Activations