© 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. 19022
    Prev
    Next
    INDEX
    Explanations

    lowest since month

    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
    æĿľåħ°
    -0.09
    åī¯å¸Ĥéķ¿
    -0.09
    лежа
    -0.09
    æľ¬æľŁ
    -0.09
    æ¯ı人
    -0.09
    ä¸įçķĻ
    -0.08
    æijĦ
    -0.08
     CONTRIBUTORS
    -0.08
    æĤ¬
    -0.08
    æľ¬å±Ĭ
    -0.08
    POSITIVE LOGITS
    æľŃ
    0.09
    æ³±
    0.09
     Molly
    0.09
    è§ij
    0.08
    Ùĥر
    0.08
     Ne
    0.08
    ä¸Ģè½®
    0.08
    寨
    0.08
    dl
    0.08
    仪
    0.08
    Activations Density 0.025%

    No Known Activations