© 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. 10302
    Prev
    Next
    INDEX
    Explanations

    likely to be

    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
    еÑĤÑĮ
    -0.09
    åģļè¿ĩ
    -0.09
    PILE
    -0.08
    æŃª
    -0.08
    çªģåıij
    -0.08
    æĺŁçº§
    -0.08
    èĬ«
    -0.08
    gos
    -0.08
    çªģçĦ¶
    -0.08
    pile
    -0.08
    POSITIVE LOGITS
    大æ¦Ĥ
    0.10
    èĤ¯å®ļä¼ļ
    0.10
    æĺİå¹´
    0.10
     inev
    0.09
    èĤ¯å®ļæĺ¯
    0.09
    æĹłçĸij
    0.09
    ç¬ĥ
    0.09
    èĪIJ
    0.09
    çļĦæł·åŃIJ
    0.09
    åıijå±ķæł¼å±Ģ
    0.09
    Activations Density 0.059%

    No Known Activations