© 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. 48917
    Prev
    Next
    INDEX
    Explanations

    tenant applications

    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
    OMEM
    -0.09
    åĪĪ
    -0.09
    æĭ¦æĪª
    -0.09
    æł¸å¿ĥæĬĢæľ¯
    -0.09
    ç²¾é«ĵ
    -0.09
    ikers
    -0.09
    èĤ©èĨĢ
    -0.09
    éĢģåĪ°
    -0.08
     Hats
    -0.08
     xúc
    -0.08
    POSITIVE LOGITS
    秣
    0.16
    秣éĩij
    0.15
    秣æĪ¿
    0.14
    åħ¥ä½ı
    0.13
    æĪ¿ä¸ľ
    0.13
    æĪ¿æºIJ
    0.13
    å±ħä½ı
    0.12
     аÑĢенд
    0.12
    åĩºç§Ł
    0.12
     tenant
    0.11
    Activations Density 0.116%

    No Known Activations