© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19659
    Prev
    Next
    INDEX
    Explanations

    represented country or team

    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
    رع
    -0.10
    leton
    -0.09
    sci
    -0.09
    æĢ§æł¼
    -0.09
    liner
    -0.09
    ida
    -0.09
    æѧ
    -0.09
    же
    -0.08
    åħħåĪĨ
    -0.08
    éĢįéģ¥
    -0.08
    POSITIVE LOGITS
    å¿ĥæĻº
    0.10
    rup
    0.09
    éħ©
    0.09
     Ñģобой
    0.09
    è¡Įä¸ļçļĦ
    0.08
    çªĹåı£
    0.08
    åıĤå±ķ
    0.08
    åıĬ缸åħ³
    0.08
    è¿Ļ个ä¸ĸçķĮ
    0.08
    /testing
    0.08
    Activations Density 0.045%

    No Known Activations