© 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. 53663
    Prev
    Next
    INDEX
    Explanations

    baked goods and desserts

    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¸įåİ»
    -0.08
    antar
    -0.08
     extras
    -0.08
    æĮĤéĴ©
    -0.08
    æķĪèĥ½
    -0.08
    èĪ¹åıª
    -0.08
    stag
    -0.08
    wu
    -0.08
     Bak
    -0.08
    .cloudflare
    -0.07
    POSITIVE LOGITS
    éĥ¾
    0.09
     schn
    0.09
    .analytics
    0.09
    æŦ
    0.09
    gether
    0.09
    hé
    0.09
    ä¸įçķĻ
    0.09
    åѦåĪ°
    0.08
    æĿ¾
    0.08
    ç¯ģ
    0.08
    Activations Density 0.009%

    No Known Activations