© 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. 2621
    Prev
    Next
    INDEX
    Explanations

    size, age, shape, duration, severity

    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
    oire
    -0.12
    å®ĥæĺ¯
    -0.11
    æĿŃ
    -0.10
    ä»ĸæĺ¯
    -0.10
    çĿĢä»ĸ
    -0.10
    æ»ļæ»ļ
    -0.10
    дел
    -0.10
    STITUTE
    -0.10
    ä¸ĢæĿ¡é¾Ļ
    -0.09
    çĭ¬çī¹çļĦ
    -0.09
    POSITIVE LOGITS
     ÙĪاÙĦتÙĬ
    0.09
    ä¸Ķ
    0.09
    被æī§è¡Į
    0.09
     Nova
    0.08
     yet
    0.08
    hiro
    0.08
     ÙĪاÙĦØ°ÙĬ
    0.08
    çµ®
    0.08
    æĬķèŀįèµĦ
    0.07
    aldi
    0.07
    Activations Density 0.235%

    No Known Activations