© 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. 1071
    Prev
    Next
    INDEX
    Explanations

    explicit or direct statements

    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
    主ä½ĵ
    -0.09
    çݳ
    -0.09
    åįķ车
    -0.09
    rap
    -0.08
    å½¹
    -0.08
     cor
    -0.08
    忽è§Ĩ
    -0.08
     yanı
    -0.08
    æĹħ
    -0.08
    忽æĤł
    -0.08
    POSITIVE LOGITS
    æĺİç¡®
    0.18
     explicit
    0.18
     explicitly
    0.17
    explicit
    0.17
    Explicit
    0.16
    æĺİç¡®æıIJåĩº
    0.15
     Explicit
    0.14
    æĺİæľĹ
    0.14
    	explicit
    0.13
    æĺİ
    0.12
    Activations Density 0.081%

    No Known Activations