© 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. 49584
    Prev
    Next
    INDEX
    Explanations

    information retrieval and tracking

    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¸įåħį
    -0.09
    wil
    -0.09
    èĻļ
    -0.08
    ç½ijç«Ļ建设
    -0.08
    BOUND
    -0.08
    IEW
    -0.08
    ç³ģ
    -0.08
    纡
    -0.08
    (er
    -0.08
     juni
    -0.08
    POSITIVE LOGITS
    æĥħ绪
    0.09
    çļĦæĥħ绪
    0.09
    è°Ī论
    0.09
     sentiment
    0.09
    çĪ¬
    0.09
    ÙĪع
    0.08
    çļĦçĭ¬çī¹
    0.08
    æĵ¢
    0.08
    èĽĽ
    0.08
    å¥ı
    0.08
    Activations Density 0.152%

    No Known Activations