© 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. 38882
    Prev
    Next
    INDEX
    Explanations

    Foles, Prescott, Cutler, Vickie

    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
    ime
    -0.09
    对æĬĹ
    -0.09
    æīª
    -0.09
    ño
    -0.08
    ä¸ĢæĬĬ
    -0.08
    webs
    -0.08
    ä¸ĢåĿĹ
    -0.08
    è°ĥåīĤ
    -0.08
    lay
    -0.08
    Ả
    -0.08
    POSITIVE LOGITS
     Heads
    0.10
    æ¦ķ
    0.09
    æĺı
    0.09
     Millenn
    0.09
    .PREFERRED
    0.09
    åĿŁ
    0.09
    漪
    0.08
    кÑĢа
    0.08
    èĹģ
    0.08
    åįģåħ«
    0.08
    Activations Density 0.021%

    No Known Activations