© 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. 19442
    Prev
    Next
    INDEX
    Explanations

    assist in

    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
    dit
    -0.13
    ç«ĭåľº
    -0.10
    çļĦçĶŁåij½
    -0.10
    é²²
    -0.10
    æĤ¬æĮĤ
    -0.10
    .opend
    -0.09
    å®Ĺ
    -0.09
    ÙħÙĤاÙĦات
    -0.09
    è¦ģåĬłå¼º
    -0.09
    æĢĢæĬ±
    -0.09
    POSITIVE LOGITS
    onian
    0.09
    åľĨ满å®ĮæĪIJ
    0.08
    åĽ½æľīèµĦ产
    0.08
    anz
    0.08
    管çIJĨå·¥ä½ľ
    0.08
    棱
    0.08
    æ¯ķ
    0.08
     viá»ĩc
    0.08
    rimp
    0.08
    .Concurrent
    0.08
    Activations Density 0.027%

    No Known Activations