© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8177
    Prev
    Next
    INDEX
    Explanations

    Senate committee

    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
    å®ŀä½ĵ
    -0.09
    管çIJĨéĥ¨éŨ
    -0.09
    åħ¬å®īæľºåħ³
    -0.09
    饴
    -0.09
    çĸĻ
    -0.09
    åħ¥èĤ¡
    -0.09
    æĶ¶æ¬¾
    -0.08
    è±ĨèħIJ
    -0.08
    è¡ĮåĪĹ
    -0.08
    å½¹
    -0.08
    POSITIVE LOGITS
    é¢ĺ主
    0.10
    åIJģ
    0.09
    yme
    0.09
    WISE
    0.09
    æĴij
    0.08
    ÑĨенÑĤÑĢ
    0.08
    åıĭ们
    0.08
     Surv
    0.08
    æĪIJç«ĭ以æĿ¥
    0.08
    åij
    0.08
    Activations Density 0.013%

    No Known Activations