© 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. 55565
    Prev
    Next
    INDEX
    Explanations

    dietary supplement instructions

    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
    å¼Ģå¿ĥ
    -0.09
    èĥ¶åĽĬ
    -0.09
    åĮĸèĤ¥
    -0.09
    空çĻ½
    -0.08
    ç»ĨåĮĸ
    -0.08
     vertical
    -0.08
     breakdown
    -0.08
    èĵĿ天
    -0.08
    ç»Ļä»ĸ们
    -0.08
    èģĮä¸ļéģĵå¾·
    -0.08
    POSITIVE LOGITS
    ãĥĵãĥ¼
    0.09
    ä¸ĸ代
    0.09
     pew
    0.09
    clide
    0.09
    èĥª
    0.09
    ç¬ķ
    0.09
    iska
    0.09
     maur
    0.09
    ظر
    0.09
    æ½®
    0.09
    Activations Density 0.012%

    No Known Activations