© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37663
    Prev
    Next
    INDEX
    Explanations

    create a new

    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
    çłº
    -0.09
    åĪ°ä½į
    -0.09
    ä¸ĩæĪ·
    -0.09
    æīĵåĩ»
    -0.09
    åĿŀ
    -0.08
    TIM
    -0.08
    æĮĩ
    -0.08
    asers
    -0.08
    çľĭä¸įåĪ°
    -0.08
    ä¸įåĪ°ä½į
    -0.08
    POSITIVE LOGITS
    ä¸Ģ个æĸ°çļĦ
    0.15
    à¹ĥหม
    0.13
    æĸ°çļĦ
    0.13
    ä¼Ĭå§ĭ
    0.11
    空çĻ½
    0.11
     new
    0.10
     новÑĭй
    0.10
    çļĦæĸ°
    0.10
    ä¸Ģè¡Į
    0.10
     blank
    0.10
    Activations Density 0.440%

    No Known Activations