© 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. 51642
    Prev
    Next
    INDEX
    Explanations

    airline / carrier

    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
    usz
    -0.10
    ú
    -0.09
    åĩºå·®
    -0.09
    eka
    -0.09
    CEE
    -0.09
    èį«
    -0.09
    è¿Ļ座åŁİå¸Ĥ
    -0.09
    å±ħä½ı
    -0.08
    é«ĺåĩº
    -0.08
    èİŀ
    -0.08
    POSITIVE LOGITS
    çł´äº§
    0.12
    æī§
    0.11
    STS
    0.10
    æī¿
    0.10
    åħ¬åı¸å°Ĩ
    0.09
    åħ¬åı¸çļĦ
    0.09
    .Operator
    0.09
    è¿IJèIJ¥
    0.09
    ä¸ļ
    0.09
    æĶ¯çº¿
    0.09
    Activations Density 0.067%

    No Known Activations