© 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. 49599
    Prev
    Next
    INDEX
    Explanations

    indonesia and java

    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
    è¾Ħ
    -0.11
    为æѤ
    -0.11
    robe
    -0.10
    hev
    -0.10
    ä¸įç»ı
    -0.10
    è¿Ļä¸ĢåĪ»
    -0.09
    -cn
    -0.09
    же
    -0.09
     Evil
    -0.09
    æĭ¼æIJı
    -0.08
    POSITIVE LOGITS
    é¹ģ
    0.09
    çĸijéļ¾
    0.08
    èļĮ
    0.08
    èľĹ
    0.08
    utan
    0.08
    gam
    0.08
     QS
    0.08
    缴èIJ¥
    0.08
    èµ·çłģ
    0.08
    主æŨ
    0.08
    Activations Density 0.060%

    No Known Activations