© 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. 48792
    Prev
    Next
    INDEX
    Explanations

    guys, girls, boys, gal

    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°¼äºļ
    -0.09
    å°ī
    -0.09
    æľ´ç´ł
    -0.08
     someone
    -0.08
     ding
    -0.08
    /command
    -0.08
    ä¸įçĶ¨
    -0.08
    ItemAt
    -0.08
    æ°ĶåĢĻåıĺåĮĸ
    -0.08
    åĮºåŁŁæĢ§
    -0.08
    POSITIVE LOGITS
    亮
    0.10
    们
    0.09
    éĻĦ
    0.09
    Bomb
    0.09
    å¸Ń
    0.08
     goose
    0.08
    _TYPEDEF
    0.08
    åIJĦèĩª
    0.08
    æĶ¾åģĩ
    0.08
    bud
    0.08
    Activations Density 0.036%

    No Known Activations