© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9056
    Prev
    Next
    INDEX
    Explanations

    galaxy, clusters, nuclei, sources

    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
    æĮ½
    -0.10
    ä¸ĥ大
    -0.10
    èij¡èIJĦ
    -0.10
    åĪĨéħį
    -0.09
    sı
    -0.09
     Sunset
    -0.09
    cle
    -0.09
     اÙĦرØŃ
    -0.09
    çī¢
    -0.08
    ä»»æĦı
    -0.08
    POSITIVE LOGITS
    atab
    0.09
    åºŁå¼ĥ
    0.09
    è¿ľç¨ĭ
    0.09
    éħ±
    0.08
    Bars
    0.08
    æĿĤ
    0.08
    ä¸Ńå¤ĸ
    0.08
    缴éĢļ车
    0.08
    è´ª
    0.08
     Cheap
    0.08
    Activations Density 0.236%

    No Known Activations