© 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. 50858
    Prev
    Next
    INDEX
    Explanations

    London face painters

    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
    åĬ¡
    -0.09
    ä¸Ģå¥Ĺ
    -0.09
    迹
    -0.09
    ä¸Ģ头
    -0.09
    è¦ģåģļ好
    -0.09
    ä¸įä½Ĩ
    -0.08
    ä¸ĢéŨ
    -0.08
    ä»ĸ们çļĦ
    -0.08
    æı½
    -0.08
    éĹ®ä¸ĸ
    -0.08
    POSITIVE LOGITS
    éĩįåŀĭ
    0.10
    æĽľ
    0.10
    ovsky
    0.09
    PropertyParams
    0.09
    liga
    0.09
    lox
    0.09
    sbin
    0.08
    èĤ¤èī²
    0.08
     Mahmoud
    0.08
    acier
    0.08
    Activations Density 0.006%

    No Known Activations