© 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. 2676
    Prev
    Next
    INDEX
    Explanations

    rooms and accommodation

    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
    仿
    -0.09
    æĭŁ
    -0.09
    欢
    -0.08
    aser
    -0.08
    å«ģ
    -0.08
    æķĻèĤ²åŁ¹è®Ń
    -0.08
    LOOP
    -0.08
    è¿Ļåĩłä¸ª
    -0.08
    aren
    -0.08
    æ°Ļ
    -0.08
    POSITIVE LOGITS
    åºĬä½į
    0.15
    çªĥ
    0.12
     locker
    0.12
    çĿ¡
    0.12
    å¯Ŀ室
    0.11
    -room
    0.11
    座ä½į
    0.11
    çªĹ
    0.11
    å¯Ŀ
    0.11
    室
    0.11
    Activations Density 0.063%

    No Known Activations