© 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. 19116
    Prev
    Next
    INDEX
    Explanations

    United States, credit, public, program

    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
    åĢ¾
    -0.10
    ä¸Ģ个个
    -0.09
    çļĦå£°éŁ³
    -0.09
    æĸĩèīº
    -0.08
    该项
    -0.08
    äºİæѤ
    -0.08
    天使
    -0.08
    éĥ¢
    -0.07
    æĮĩçĤ¹
    -0.07
    oley
    -0.07
    POSITIVE LOGITS
    认åı¯
    0.11
    ä¸Ģä¸ĸ
    0.10
    é¢ģåıij
    0.10
    åѦåİĨ
    0.10
    åı¯ä¿¡
    0.10
    注æĺİåĩºå¤Ħ
    0.10
    大åѦæ¯ķä¸ļ
    0.09
    è¡Ķæİ¥
    0.09
    ç£Ĭ
    0.09
    æī¿è®¤
    0.09
    Activations Density 0.050%

    No Known Activations