© 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. 37391
    Prev
    Next
    INDEX
    Explanations

    DC Comics characters and titles

    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
    ç±³ç²ī
    -0.09
    èī²ç´ł
    -0.08
    çľĭæĿ¥
    -0.08
    çĬĴ
    -0.08
    æĶ¿åħļ
    -0.08
     Conspiracy
    -0.08
    íĥĦ
    -0.08
    好åĥı
    -0.08
    SID
    -0.08
    åIJĮçŃī
    -0.08
    POSITIVE LOGITS
    à¸Ńาย
    0.09
    ione
    0.09
    æ¡£
    0.09
    仪åĻ¨
    0.09
    æ¯Ķäºļ
    0.09
    ÑĤел
    0.09
    /Home
    0.09
    elly
    0.08
    åģĩæĹ¥
    0.08
    åĭĻ
    0.08
    Activations Density 0.147%

    No Known Activations