© 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. 32855
    Prev
    Next
    INDEX
    Explanations

    would like or would do

    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
    éĺĶ
    -0.09
    å²IJ
    -0.08
    æ¶Īè´¹
    -0.08
    éĵĨ
    -0.08
    æ¶Īè²»
    -0.08
     supposed
    -0.08
     Rim
    -0.08
    æĮĩåIJij
    -0.08
    æºĺ
    -0.08
    éĽ¾éľ¾
    -0.07
    POSITIVE LOGITS
    ä¸įä¼ļæľī
    0.09
    .creator
    0.09
    身边çļĦ
    0.09
    人éĢī
    0.09
    odate
    0.09
    notated
    0.09
    eldo
    0.09
    ä¸Ģç»ı
    0.09
    客æĪ·æıIJä¾Ľ
    0.09
    ãĤĴä½ľãĤĭ
    0.09
    Activations Density 0.029%

    No Known Activations