© 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. 20802
    Prev
    Next
    INDEX
    Explanations

    public policy or interest

    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
    æ¦ķ
    -0.10
    èĩªåıij
    -0.10
     Mam
    -0.09
     Trev
    -0.09
    unate
    -0.09
    åIJijçĿĢ
    -0.09
    æ·±åĬłå·¥
    -0.09
    红线
    -0.09
    好åIJĥ
    -0.08
    æ§Į
    -0.08
    POSITIVE LOGITS
    2
    0.09
    8
    0.09
    èĥ¥
    0.09
    容å¿į
    0.09
    é¢ģåıij
    0.09
    èĢĥèĻij
    0.09
    .zh
    0.08
    3
    0.08
     considerations
    0.08
    ä¿¡èµĸ
    0.08
    Activations Density 0.090%

    No Known Activations