© 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. 35749
    Prev
    Next
    INDEX
    Explanations

    much of the

    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
    ä¸ĩä¸Ģ
    -0.09
    è¯Ĩ
    -0.09
    pps
    -0.09
    å¤ļæł·åĮĸ
    -0.08
    eren
    -0.08
    pon
    -0.08
    è¿«
    -0.08
    anj
    -0.08
    åĪ«çļĦ
    -0.08
    !--
    -0.08
    POSITIVE LOGITS
    inery
    0.10
    _FMT
    0.09
    åıĸåĨ³äºİ
    0.09
    åĩĨå¤ĩå·¥ä½ľ
    0.09
    å¾ĹçĽĬäºİ
    0.09
    çļĦæĦŁåıĹ
    0.09
    æĪij们éĥ½
    0.09
    çļĦä¼ĺåĬ¿
    0.09
    第ä¸īèĬĤ
    0.09
    çļĦç¼ĺ
    0.08
    Activations Density 0.169%

    No Known Activations