© 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. 63327
    Prev
    Next
    INDEX
    Explanations

    enterprise resource planning

    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
    ç§ijåѦéĻ¢
    -0.09
    ETA
    -0.09
    æĺ§
    -0.09
    éĢłç¦ı
    -0.08
    æıŃ
    -0.08
    åĽŃ
    -0.08
    راÙĤ
    -0.08
    veloper
    -0.08
     dia
    -0.08
    åľĴ
    -0.08
    POSITIVE LOGITS
    è´¢åĬ¡
    0.16
    è´¢åĬ¡ç®¡çIJĨ
    0.14
    è´¢ç¨İ
    0.13
     finance
    0.12
     marketing
    0.12
     Marketing
    0.11
    finance
    0.11
    èIJ¥éĶĢ
    0.11
    Marketing
    0.10
     اÙĦÙħاÙĦÙĬØ©
    0.10
    Activations Density 0.055%

    No Known Activations