© 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. 10965
    Prev
    Next
    INDEX
    Explanations

    UFC

    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
    侯
    -0.11
    ãģĹãģ¾ãģĨ
    -0.09
     thá»Ŀ
    -0.08
    åıŁ
    -0.08
    elry
    -0.08
    aled
    -0.08
    alist
    -0.08
    APT
    -0.08
    lik
    -0.08
    足åįı
    -0.08
    POSITIVE LOGITS
    APS
    0.09
    æĬĬè¿Ļ个
    0.08
    uent
    0.08
    ä»ħä¾Ľ
    0.08
    inke
    0.08
    åįģäºĶ
    0.08
    mpr
    0.08
    ste
    0.08
    ä¸Ńå¤ĸ
    0.08
    ÑĦоÑĢ
    0.08
    Activations Density 0.007%

    No Known Activations