© 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. 48253
    Prev
    Next
    INDEX
    Explanations

    theatre performances

    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
    马æĭīæĿ¾
    -0.08
     Tome
    -0.08
    scoped
    -0.08
    suma
    -0.08
    Clo
    -0.08
    bpp
    -0.08
    骤
    -0.08
    åĨ³
    -0.08
    ÑĢаз
    -0.08
    omat
    -0.08
    POSITIVE LOGITS
    æ¼Ķåĩº
    0.20
    表æ¼Ķ
    0.16
    ä¸Ĭæ¼Ķ
    0.12
    æ¼Ķ
    0.12
    æ¼Ķèīº
    0.12
     performances
    0.11
    åĶ®
    0.11
     trou
    0.11
    æ¼Ķç»İ
    0.11
     performance
    0.11
    Activations Density 0.129%

    No Known Activations