© 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. 57188
    Prev
    Next
    INDEX
    Explanations

    jerseys and tattoos

    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
    æĭīå¼Ģ
    -0.09
    è¸ıåħ¥
    -0.09
    elps
    -0.09
    çľ¼åīįçļĦ
    -0.09
    身边çļĦ
    -0.09
    ior
    -0.09
    æ¥Ķ
    -0.09
    éĢļ讯åijĺ
    -0.08
    Touchable
    -0.08
    æ¯ı次
    -0.08
    POSITIVE LOGITS
    纹
    0.12
    åį°
    0.11
    éķĮ
    0.10
    æĪIJé¾Ļ
    0.10
    è¡«
    0.09
     tattoos
    0.09
    æĹı
    0.09
    忸
    0.09
    reserved
    0.09
    æĪĺéĺŁ
    0.09
    Activations Density 0.157%

    No Known Activations