© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37069
    Prev
    Next
    INDEX
    Explanations

    weight loss and nutrition

    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
    å«Į
    -0.11
    æĥ©
    -0.11
    è·Ľ
    -0.10
    ä¸Ģ页
    -0.10
    箩
    -0.10
    ervo
    -0.09
    è´¯éĢļ
    -0.09
    蹩
    -0.09
    å¹³æ°ij
    -0.09
    æ»Ķ
    -0.09
    POSITIVE LOGITS
    çĺ¦
    0.17
    æĨĶ
    0.09
    å»ĭ
    0.09
     Colum
    0.09
     starvation
    0.08
     skinny
    0.08
    zion
    0.08
    æķĻæĿIJ
    0.08
    als
    0.08
     ca
    0.08
    Activations Density 0.079%

    No Known Activations