© 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. 38116
    Prev
    Next
    INDEX
    Explanations

    man

    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¿Ń
    -0.11
    éĴ¿
    -0.11
    æ»Ĥ
    -0.10
    空ä¸Ń
    -0.10
    约ä¼ļ
    -0.09
    鹫
    -0.09
    çī¢
    -0.09
    磼
    -0.09
    åĪ«äººçļĦ
    -0.09
    åĬª
    -0.09
    POSITIVE LOGITS
    би
    0.09
    aces
    0.09
    èĦĤ
    0.08
    ivre
    0.08
    æ¼ı
    0.08
    lig
    0.08
    éĿ¢èī²
    0.08
    é«ĺç´łè´¨
    0.08
    æľīæĦı
    0.08
    Gas
    0.08
    Activations Density 0.041%

    No Known Activations