© 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. 61473
    Prev
    Next
    INDEX
    Explanations

    remained unchanged

    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
    强迫
    -0.09
     Schneider
    -0.09
    åŁ¹
    -0.09
    梨
    -0.08
    åŃ¥
    -0.08
    ç²¹
    -0.08
    佩
    -0.08
    èı±
    -0.08
    缺å¸Ń
    -0.08
    溯
    -0.08
    POSITIVE LOGITS
    ä¸įåıĺ
    0.17
    å¾ĺå¾Ĭ
    0.12
    ä¸įåĬ¨
    0.12
    稳å®ļçļĦ
    0.11
    æŁŀ
    0.11
    unch
    0.11
    å°ıå¹ħ
    0.10
    å·¡èĪª
    0.10
    ç»´æĮģ
    0.10
     unchanged
    0.10
    Activations Density 0.078%

    No Known Activations