© 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. 57524
    Prev
    Next
    INDEX
    Explanations

    days or periods of time

    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
    å½Ĵ
    -0.09
    lep
    -0.09
    åľºåĿĩ
    -0.08
    æ¿Ĵ
    -0.08
    饶
    -0.08
    æѸ
    -0.08
    ä»İå°ı
    -0.08
    éĢIJæ¸IJ
    -0.08
    éĢIJæŃ¥
    -0.08
    çĶŁæŃ»
    -0.08
    POSITIVE LOGITS
    å½ĵ天
    0.16
    è¿Ļä¸Ģ天
    0.15
    éĤ£ä¸Ģ天
    0.13
    éĤ£å¤©
    0.13
    ä»Ĭ天
    0.12
    åīįä¸Ģ天
    0.12
    å¿ĥæĥħ
    0.11
    è¿Ļ两天
    0.11
    ä»Ĭ天çļĦ
    0.11
    ä»ĬæĹ¥ãģ¯
    0.11
    Activations Density 0.167%

    No Known Activations