© 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. 37938
    Prev
    Next
    INDEX
    Explanations

    mixing together and then

    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
    stance
    -0.10
    ibaba
    -0.10
    awan
    -0.09
    æĻļ
    -0.09
    åij¼åı«
    -0.09
    awks
    -0.09
    è·»
    -0.09
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.09
    åij¼ãģ°
    -0.09
    åĵ¨
    -0.09
    POSITIVE LOGITS
    å¾Ĺåĩº
    0.09
    ness
    0.09
    å°º
    0.09
     strands
    0.08
    äºĨ
    0.08
     зан
    0.08
    StyleSheet
    0.08
    æī¶
    0.08
    åīįä¸ĸ
    0.08
    ä»ĩ
    0.08
    Activations Density 0.002%

    No Known Activations