© 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. 62676
    Prev
    Next
    INDEX
    Explanations

    sentence endings or beginnings

    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
    ãĤ®ãĥ£
    -0.09
    妫
    -0.09
    åĩĨ
    -0.09
    æľ½
    -0.08
    rys
    -0.08
    éľŃ
    -0.08
    çĽ¸ä¼¼
    -0.08
    åijĻ
    -0.08
    oric
    -0.08
    åħ¥æĪ·
    -0.08
    POSITIVE LOGITS
    çļĦæĦıä¹ī
    0.11
    çݩ家æĿ¥è¯´
    0.11
    åįģåĪĨéĩįè¦ģ
    0.10
    éĿŀ常éĩįè¦ģ
    0.10
    æĦıä¹ī
    0.10
    è¿ĻäºĽäºº
    0.10
    çļĦ人æĿ¥è¯´
    0.09
    çĽĤ
    0.09
    对æĪij说
    0.09
    æĦı義
    0.09
    Activations Density 0.038%

    No Known Activations