© 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. 23206
    Prev
    Next
    INDEX
    Explanations

    on the court or field

    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
     Canal
    -0.09
    ãģĦãģ§
    -0.09
    读åIJİ
    -0.09
    çľ¼çļ®
    -0.09
    天é¹ħ
    -0.09
    ìĬ¬
    -0.08
    éĥħ
    -0.08
    çľ¼åħī
    -0.08
    课åłĤæķĻåѦ
    -0.08
    èĩ³ä¸Ĭ
    -0.08
    POSITIVE LOGITS
    ä¸ĬçļĦ
    0.16
    æīª
    0.10
    ä¸Ĭãģ®
    0.09
    ä¸Ĭæľī
    0.09
    çĥĤ
    0.09
    fusc
    0.08
    使çĶ¨æĿĥ
    0.08
    agnar
    0.08
     wax
    0.08
    ç¾Ķ
    0.08
    Activations Density 0.010%

    No Known Activations