© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9304
    Prev
    Next
    INDEX
    Explanations

    decided to

    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
    æĢħ
    -0.09
    âĿ£
    -0.09
     Morm
    -0.09
    æģ¬
    -0.09
    /dom
    -0.09
    plier
    -0.09
    ảnh
    -0.09
     اÙĦÙĪز
    -0.09
    asso
    -0.09
    ÐľÐŀ
    -0.09
    POSITIVE LOGITS
    æľīå¿ħè¦ģ
    0.12
    æĹ¢çĦ¶
    0.10
    è¦ģåģļ
    0.10
    nek
    0.09
    dek
    0.09
    太ä¹ħ
    0.09
    太
    0.09
     too
    0.09
    åĢ¼å¾Ĺä¸Ģ
    0.09
    ëĭĪê¹Į
    0.09
    Activations Density 0.034%

    No Known Activations