© 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. 33280
    Prev
    Next
    INDEX
    Explanations

    numbers followed by lists

    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
    ä¸Ģç»Ħ
    -0.09
    çij°
    -0.09
    åIJĦé¡¹å·¥ä½ľ
    -0.09
    ä¹Łæľīå¾Īå¤ļ
    -0.09
    æľī许å¤ļ
    -0.09
    ä¸ĢåľĪ
    -0.09
    çļĦåIJĦç§į
    -0.09
    ç²ij
    -0.09
    åŀ£
    -0.09
    çļĦåIJĦ项
    -0.08
    POSITIVE LOGITS
    åīįæīĢ
    0.09
    ä¸įéĶĻçļĦ
    0.09
    æĢĿ念
    0.09
     Kurd
    0.09
    çī¹æ®ĬçļĦ
    0.08
    rens
    0.08
    æģ©
    0.08
    èĵ¼
    0.08
    osity
    0.08
    æĿİåħĪçĶŁ
    0.08
    Activations Density 0.054%

    No Known Activations