© 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. 63073
    Prev
    Next
    INDEX
    Explanations

    according to studies and statistics

    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¸Ģä½ĵ
    -0.12
    à¨Ĩ
    -0.11
    çİ°å®ŀä¸Ń
    -0.10
    ivery
    -0.09
    à¸Ńะ
    -0.09
    ç£ĭåķĨ
    -0.09
    è¾ķ
    -0.08
    åIJĬ
    -0.08
     Maher
    -0.08
    ugs
    -0.08
    POSITIVE LOGITS
    æĥħåĨµæĿ¥çľĭ
    0.11
    èµĦæĸĻæĺ¾ç¤º
    0.11
    没éĶĻ
    0.09
    æīĢ说
    0.08
    åĬ©æīĭ
    0.08
    ä¸įéĶĻçļĦ
    0.08
    å°±è¿ŀ
    0.08
    åIJĪä¼Ļ人
    0.08
    çļĦ说æ³ķ
    0.08
    ä¿Ŀå§Ĩ
    0.08
    Activations Density 0.101%

    No Known Activations