© 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. 50761
    Prev
    Next
    INDEX
    Explanations

    in custody

    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
    оÑģÑĮ
    -0.10
    ä¸ŃéĢĶ
    -0.10
    agle
    -0.09
    ä¸ŃéĹ´
    -0.09
    etty
    -0.09
    äºĨä¸Ģåı¥
    -0.09
    ÑģÑı
    -0.08
    ãģ¾ãģĻãģĮ
    -0.08
    itud
    -0.08
    ster
    -0.08
    POSITIVE LOGITS
    raid
    0.09
    人åĵ¡
    0.09
    å°ıé¢Ŀ
    0.09
    rip
    0.08
    enet
    0.08
    ierung
    0.08
    _subtype
    0.08
     tả
    0.08
    ä¸ĢåIJį
    0.08
    ("~/
    0.08
    Activations Density 0.004%

    No Known Activations