© 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. 38228
    Prev
    Next
    INDEX
    Explanations

    dates with months

    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
    ụ
    -0.09
    媵
    -0.09
    èIJľ
    -0.09
    æĢ»éĺŁ
    -0.08
    \.
    -0.08
    rame
    -0.08
    åĺŀ
    -0.08
    odore
    -0.08
    çĩĥ
    -0.08
    èĨĪ
    -0.08
    POSITIVE LOGITS
    æĴ¼
    0.10
    人们对
    0.09
    åĽºçĦ¶
    0.09
    çīĪæĿĥå½Ĵ
    0.09
    å¿«æĬ¥
    0.09
    ewise
    0.09
    ä¹Łå¥½
    0.09
    vell
    0.09
    å·²ç»ıåľ¨
    0.09
     zwar
    0.08
    Activations Density 0.130%

    No Known Activations