© 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. 49517
    Prev
    Next
    INDEX
    Explanations

    Verizon, Telstra, 6, 9

    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
    æĪijåıijçİ°
    -0.09
    è±ī
    -0.09
    avers
    -0.09
    еÑĢиал
    -0.09
    æĦŁæ¿Ģ
    -0.09
    ä»Ģä¹Īåij¢
    -0.09
    fully
    -0.08
    åIJİåį«
    -0.08
    inning
    -0.08
    _trap
    -0.08
    POSITIVE LOGITS
    -Benz
    0.10
    ä¸įä¿¡
    0.09
    etta
    0.09
    аÑİÑĤÑģÑı
    0.08
    wig
    0.08
    ált
    0.08
     اÙĦÙĥبرÙī
    0.08
    rag
    0.08
    оÑĩнÑĭе
    0.08
    /Main
    0.08
    Activations Density 0.001%

    No Known Activations