© 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. 2152
    Prev
    Next
    INDEX
    Explanations

    Olympics Summer Winter song

    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
    失
    -0.10
     hydr
    -0.10
    inois
    -0.09
    Unnamed
    -0.09
    iland
    -0.09
    éĥ§
    -0.09
    omore
    -0.09
    ipse
    -0.09
    _MEDIUM
    -0.08
    erness
    -0.08
    POSITIVE LOGITS
    æĮ½
    0.10
    æĿ¥äºĨ
    0.10
    åľºé¦Ĩ
    0.09
    æĮĩåįĹ
    0.09
    athlete
    0.09
    Fit
    0.09
     fit
    0.09
    åĸĿäºĨ
    0.09
    奥è¿IJä¼ļ
    0.09
    è¹´
    0.09
    Activations Density 0.118%

    No Known Activations