© 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. 18146
    Prev
    Next
    INDEX
    Explanations

    second and final

    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
    uld
    -0.08
    驹
    -0.08
     pareja
    -0.08
    ç½ijç«Ļåľ°åĽ¾
    -0.08
    è¿ĩåİ»
    -0.08
    ZONE
    -0.08
    èĬŁ
    -0.08
    tras
    -0.08
    æĭĽåķĨå¼ķèµĦ
    -0.07
    èł²
    -0.07
    POSITIVE LOGITS
    大èĤ¡ä¸ľ
    0.11
    è§Ħ模æľĢ大
    0.11
    اÙĨÙĬ
    0.09
    åIJĮæĹ¶ä¹Łæĺ¯
    0.09
    è¦ģåģļ
    0.09
    åį°è±¡
    0.09
    æŃ¦å£«
    0.09
    浪漫
    0.09
    urst
    0.09
    åѦçĶŁä»¬
    0.08
    Activations Density 0.065%

    No Known Activations