© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 57279
    Prev
    Next
    INDEX
    Explanations

    Al-Qaeda, ISIS, Boko Haram, Laden

    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
    åİ¿åħ¬å®īå±Ģ
    -0.10
    产åѦçłĶ
    -0.09
    åİ¿æĶ¿åºľ
    -0.09
    ä¸įåĩºæĿ¥
    -0.09
    ä»Ģä¹Īåij¢
    -0.09
    äºĶæĺŁ
    -0.09
    åĽ½äºº
    -0.09
    好åIJĹ
    -0.09
    æĺ¯ä¸Ģä½į
    -0.08
    onal
    -0.08
    POSITIVE LOGITS
    жи
    0.09
    IZER
    0.08
    orphic
    0.08
    (dy
    0.08
    ÑĢова
    0.08
    ged
    0.08
    åı£ä¸Ń
    0.08
    çĶ¨äºº
    0.08
    croft
    0.08
    ä¾ı
    0.08
    Activations Density 0.004%

    No Known Activations