© 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. 54556
    Prev
    Next
    INDEX
    Explanations

    health, technology, and daily life topics

    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
    ä»İä¸Ń
    -0.11
    å¤ĸæĿ¥
    -0.09
    å®ĥçļĦ
    -0.09
    è¿ĺæĥ³
    -0.08
    nut
    -0.08
    imate
    -0.08
    -thinking
    -0.08
    åħ¶å®ĥ
    -0.08
    ayo
    -0.08
     indem
    -0.08
    POSITIVE LOGITS
    æľīäºĨ
    0.10
    deen
    0.09
    è¶Ĭæĺ¯
    0.09
    èĹľ
    0.09
     Kelley
    0.08
    ä¸įä»ħ
    0.08
    å§Ķåijĺä¼ļ
    0.08
    cts
    0.08
    GEST
    0.08
     premiere
    0.08
    Activations Density 0.592%

    No Known Activations