© 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. 6647
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Muj
    -0.10
    å¦Ĭå¨ł
    -0.09
    Tau
    -0.09
    èĥİ
    -0.09
     Saud
    -0.09
    社åĮº
    -0.09
    å·¾
    -0.08
    æĭīæĸ¯
    -0.08
    vo
    -0.08
    æ²±
    -0.08
    POSITIVE LOGITS
    æīĺ管
    0.10
     коÑĢпÑĥÑģ
    0.09
    顾
    0.09
    çĪ¸å¦Ī
    0.09
    åĪĩ
    0.09
    ius
    0.09
    éĿĴéĵľ
    0.09
    漪
    0.09
    大åŁİå¸Ĥ
    0.08
    纶
    0.08
    Activations Density 0.038%

    No Known Activations