© 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. 54901
    Prev
    Next
    INDEX
    Explanations

    invite you to

    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
    è¾ĸåĮºåĨħ
    -0.10
    ะ
    -0.09
    å¿Ļç¢Į
    -0.09
    tsky
    -0.09
    æĶ¸
    -0.09
    干活
    -0.09
    大大å°ıå°ı
    -0.09
    æ³Ľ
    -0.09
    ä¸Ģè´¯
    -0.09
    åIJĥè¿ĩ
    -0.09
    POSITIVE LOGITS
    è®¤çľŁåŃ¦ä¹ł
    0.09
    ä»Ķç»Ĩ
    0.09
    åĬłåħ¥
    0.09
    oses
    0.08
    å°½æĹ©
    0.08
    ä¸įè¦ģ
    0.08
    åħ³æ³¨
    0.08
    andon
    0.08
    anton
    0.08
     Patent
    0.08
    Activations Density 0.021%

    No Known Activations