© 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. 35845
    Prev
    Next
    INDEX
    Explanations

    java, .bukkit, .annotations

    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
    纳
    -0.09
     Fiat
    -0.09
    çİ»çĴĥ
    -0.08
    ç´į
    -0.08
    ä¸įåıĬ
    -0.08
    çĦļ
    -0.08
    éħ¬
    -0.08
    æĦı大
    -0.08
    iazza
    -0.08
     vu
    -0.08
    POSITIVE LOGITS
    欢è¿İæĤ¨
    0.10
    交éĢļæŀ¢çº½
    0.10
    propri
    0.10
    çıĪ
    0.09
    貫
    0.09
     Warwick
    0.09
    ecz
    0.09
    ×ķת
    0.09
    _SYMBOL
    0.09
    ardi
    0.09
    Activations Density 0.133%

    No Known Activations