© 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. 61179
    Prev
    Next
    INDEX
    Explanations

    ball games

    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«Ļ
    -0.08
    æ¼ı
    -0.08
    å¹´è½»çļĦ
    -0.08
    кал
    -0.08
    -character
    -0.08
    ame
    -0.08
    祺
    -0.07
    åļ
    -0.07
    常è§ģçļĦ
    -0.07
    æĭĩæĮĩ
    -0.07
    POSITIVE LOGITS
    糸
    0.11
    æĵ¦
    0.09
    å¼¹æĢ§
    0.09
    æ·ŀ
    0.09
    è¨Ģè¯Ń
    0.09
    æīĵæĭĽåij¼
    0.09
    åĪ©åĻ¨
    0.09
    ç©¿éĢı
    0.09
    追éĢIJ
    0.09
     PREF
    0.09
    Activations Density 0.041%

    No Known Activations