© 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. 4050
    Prev
    Next
    INDEX
    Explanations

    what is

    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
    æĺİ顯
    -0.09
    森
    -0.08
    èĮ¬
    -0.08
    æĺİæĺ¾
    -0.08
    æĮ¤åİĭ
    -0.08
    ä¸Ģåī¯
    -0.08
    ãģ¿ãģŁãģĦ
    -0.08
    æĪij羣çļĦ
    -0.08
    çħ¤
    -0.08
    åįģ足
    -0.08
    POSITIVE LOGITS
    æĥķ
    0.10
    opro
    0.09
    crate
    0.09
    è²Ĥ
    0.08
    ante
    0.08
    å¯Ħ
    0.08
    æĪ´
    0.08
    .uri
    0.08
    çĻ»åľº
    0.08
     Tar
    0.08
    Activations Density 0.106%

    No Known Activations