© 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. 50368
    Prev
    Next
    INDEX
    Explanations

    latest updates and news

    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
    é¦ĸå±Ĭ
    -0.11
    ä¸ĭåįĬ
    -0.11
    åīįæıIJ
    -0.11
    ä¸Ģå¼Ģå§ĭå°±
    -0.11
    è´ŀ
    -0.10
    ä¸Ģå¼Ģå§ĭ
    -0.09
    ä¸Ģ度
    -0.09
     earlier
    -0.09
    éĶ¢
    -0.09
    çģĮ
    -0.09
    POSITIVE LOGITS
    /latest
    0.12
    Latest
    0.11
    èİ«è¿ĩäºİ
    0.10
    latest
    0.10
    è£ģ
    0.10
    åĩºçĤī
    0.10
    æľĢæĸ°çļĦ
    0.10
    .latest
    0.09
     newest
    0.09
    ä»ĸ们éĥ½
    0.09
    Activations Density 0.068%

    No Known Activations