© 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. 37142
    Prev
    Next
    INDEX
    Explanations

    historical birth dates and publications

    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
    èĩ³æѤ
    -0.11
    ãģĬäºĴ
    -0.11
    ãĤ¢ãĥ¡ãĥª
    -0.10
    ç¾İåij³ãģĹ
    -0.10
    âģĪ
    -0.10
    å°±æѤ
    -0.09
    ãģ©ãĤĵãģ©
    -0.09
    ãĤİ
    -0.09
    èµĦæºIJä¼ĺåĬ¿
    -0.09
    è¿ĺä¸į
    -0.09
    POSITIVE LOGITS
    çŃīçŃī
    0.13
     etc
    0.10
    å¹²èĦĨ
    0.09
    —all
    0.09
     undisclosed
    0.08
     vet
    0.07
    æĽ´æĺ¯
    0.07
     sa
    0.07
    åĪĻ
    0.07
    ilar
    0.07
    Activations Density 0.589%

    No Known Activations