© 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. 1995
    Prev
    Next
    INDEX
    Explanations

    organization, family, team, group, store, website

    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
    å½¹
    -0.09
    ety
    -0.08
    los
    -0.08
    fr
    -0.08
    rah
    -0.08
    æĸ¹éĿ¢çļĦ
    -0.08
    æĸ¹éĿ¢
    -0.08
    rial
    -0.08
    aset
    -0.08
    verty
    -0.08
    POSITIVE LOGITS
    æĶ»åĬ¿
    0.10
    çĭ¬æľīçļĦ
    0.09
    æĸ°ä¸Ģè½®
    0.09
    åħ¨ä½ĵåijĺå·¥
    0.09
    ä¸»å¼ł
    0.09
    ä¸įä¸Ĭ
    0.09
    åĴĮä»ĸçļĦ
    0.09
    æľīä¸įå°ij
    0.09
    ä¸įå¿į
    0.09
    æĹĥ
    0.09
    Activations Density 0.169%

    No Known Activations