© 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. 27998
    Prev
    Next
    INDEX
    Explanations

    healthier food and body

    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
    çĨŁ
    -0.10
    å¸ĥç½®
    -0.09
    èĬ±çĵ£
    -0.09
    è¦ĨçĽĸçİĩ
    -0.08
    ä¸ĭ次
    -0.08
    å¤ĸè¯Ń
    -0.08
     Ritch
    -0.08
    Ñģк
    -0.08
    æ·±æĥħ
    -0.08
    éĻĶ
    -0.08
    POSITIVE LOGITS
    èĦĤèĤª
    0.12
    身ä½ĵåģ¥åº·
    0.12
    åģ¥åº·
    0.11
    еÑĢÑĮ
    0.11
     physique
    0.11
    ä½ĵè´¨
    0.11
    秤
    0.10
    ä½ĵéĩį
    0.10
     adip
    0.10
    容è²Į
    0.10
    Activations Density 0.058%

    No Known Activations