© 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. 2760
    Prev
    Next
    INDEX
    Explanations

    wearable electronic devices and computers

    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
    elm
    -0.09
    é¦ĸåĪĽ
    -0.09
    ä¸Ģå¹ħ
    -0.08
    åīIJ
    -0.08
    vara
    -0.08
    蹬
    -0.08
    çŃĸ
    -0.08
    å·¥èīº
    -0.08
    æ¯Ķè¾ĥå¤ļ
    -0.08
    æį¶
    -0.08
    POSITIVE LOGITS
    phony
    0.10
    æĻ®åıĬ
    0.10
    æ¶ĪèĢĹ
    0.09
    æ¶Īè²»
    0.09
    ä»Ĩ
    0.09
    BaseContext
    0.09
    è¡¥é½IJ
    0.09
    客åİħ
    0.09
    é¢ĨåŁŁ
    0.09
    èģĶç³»æĸ¹å¼ı
    0.09
    Activations Density 0.411%

    No Known Activations