© 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. 57043
    Prev
    Next
    INDEX
    Explanations

    diet and weight loss medication

    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
    æ¼ł
    -0.10
    åĸľ
    -0.10
    éŀĺ
    -0.10
     tầm
    -0.09
    龸
    -0.09
    inki
    -0.09
    æĹłéļľç¢į
    -0.09
    æģ°å¥½
    -0.09
    éĻ¢éĻ¢å£«
    -0.09
    ìķµ
    -0.09
    POSITIVE LOGITS
    åĩıèĤ¥
    0.21
    çĺ¦èº«
    0.18
    çĺ¦
    0.15
    ãĥĢãĤ¤ãĤ¨ãĥĥãĥĪ
    0.13
    ä½ĵéĩį
    0.13
    .Weight
    0.10
    èĦĤèĤª
    0.09
     Weight
    0.09
     diet
    0.09
     Skinny
    0.09
    Activations Density 0.245%

    No Known Activations