© 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. 49452
    Prev
    Next
    INDEX
    Explanations

    e-commerce, e-mail, e-services

    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
    æŁ´
    -0.09
    è¡Įãģ£ãģŁ
    -0.09
    shire
    -0.09
    涨价
    -0.08
    åºĬä¸Ĭ
    -0.08
    çĶµèĦij
    -0.08
    æīĭä¸ĭ
    -0.08
    ãģĦãģ£ãģŁ
    -0.08
    loggedin
    -0.08
    ãĥĥãĥī
    -0.08
    POSITIVE LOGITS
    çĶŁæ´»ä¹łæĥ¯
    0.10
    åħ´å¥ĭ
    0.10
    å¾Ĺèµ·
    0.10
    沤
    0.09
    ESIS
    0.09
    æĹ¶ä»£çļĦ
    0.09
    çĩĥ
    0.09
    tron
    0.09
    èĦĨ
    0.08
    Disappear
    0.08
    Activations Density 0.028%

    No Known Activations