© 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. 10265
    Prev
    Next
    INDEX
    Explanations

    configured, designed, adapted

    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
    çļĦåĪ°æĿ¥
    -0.09
    åŃĺåľ¨çĿĢ
    -0.09
    elize
    -0.09
    æľĭ
    -0.09
    çļĦ身影
    -0.08
    åĩºçĤī
    -0.08
    æ£Ģ
    -0.08
    ugo
    -0.08
    è§Ī
    -0.08
    èĢĮåIJİ
    -0.08
    POSITIVE LOGITS
    ippi
    0.10
    ä¸ĵéŨ
    0.10
    èµ°åIJij
    0.09
    [op
    0.09
    лиÑĤ
    0.09
    æĶ¯æĮģ
    0.09
    æİ¥åıĹ
    0.09
    滾
    0.09
    íĬ¹
    0.08
    .Container
    0.08
    Activations Density 0.130%

    No Known Activations