© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36580
    Prev
    Next
    INDEX
    Explanations

    .net, .cn, .com domains

    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
    ãģĤãĤĬ
    -0.09
    è§ĤæľĽ
    -0.09
    åĬ¨æĦŁ
    -0.08
    æļĤç¼ĵ
    -0.08
    Gil
    -0.08
    çħ§
    -0.08
    éģ¥è¿ľ
    -0.08
    çī©èµĦ
    -0.08
     bo
    -0.08
    è´µéĩijå±ŀ
    -0.08
    POSITIVE LOGITS
    illa
    0.09
    .maven
    0.09
    æµ·
    0.09
    ç²¾éĢī
    0.09
    éĢģæĸĻ
    0.08
    ILLA
    0.08
    è¶Ĭè¿ĩ
    0.08
    èĤ¢ä½ĵ
    0.08
    åIJĪä¼Ļ人
    0.08
    idl
    0.08
    Activations Density 0.109%

    No Known Activations