© 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. 4908
    Prev
    Next
    INDEX
    Explanations

    horsemen of the apocalypse

    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
    ogue
    -0.10
    æĿĥçĽĬ
    -0.09
    ä¸Ģ举
    -0.09
    å®īåħ¨ä¿Ŀéļľ
    -0.09
    åī²
    -0.09
    yny
    -0.09
    è¶ĭ
    -0.09
     yönel
    -0.08
    çıª
    -0.08
    å°ıå¾®
    -0.08
    POSITIVE LOGITS
    çĺŁ
    0.11
    æŃ»
    0.11
    çĸ«
    0.11
    çĸ«æĥħ
    0.10
    инÑĦ
    0.10
    æļ´
    0.10
    çĸ¾çĹħ
    0.10
     disease
    0.10
     fac
    0.10
    ä¼łæŁĵçĹħ
    0.10
    Activations Density 0.061%

    No Known Activations