© 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. 17639
    Prev
    Next
    INDEX
    Explanations

    duration or time frames

    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
    稷
    -0.09
    _guess
    -0.08
    æ¼Ķ
    -0.08
    æĻ¾
    -0.08
    ling
    -0.08
    steen
    -0.08
     Lanc
    -0.08
    ä¸Ģ项
    -0.08
    è¿Ļ座
    -0.08
    大ä¼Ĺ
    -0.08
    POSITIVE LOGITS
    å·²ä¹ħçļĦ
    0.11
    å¤ļå¹´çļĦ
    0.11
    å¾Īä¹ħ
    0.10
    å¤ļå¹´
    0.10
    ä»Ģä¹ĪåİŁåĽł
    0.09
    ä¸įåıĬ
    0.09
    åįĬ天
    0.09
    å·²ä¹ħ
    0.09
    许ä¹ħ
    0.09
    è¾ĥ强çļĦ
    0.09
    Activations Density 0.023%

    No Known Activations