© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6029
    Prev
    Next
    INDEX
    Explanations

    support structures, legs, or bases

    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
    æĭį
    -0.11
    饴
    -0.09
    ราย
    -0.09
    æĢģ度
    -0.09
    åŁĥå°Ķ
    -0.09
    æĹĨ
    -0.09
    éĹŃçݯ
    -0.09
    æŀŃ
    -0.09
    è´¯éĢļ
    -0.08
    å°º
    -0.08
    POSITIVE LOGITS
    èĦļ
    0.11
     Jub
    0.10
    èħ¿
    0.10
    èĦļä¸ĭ
    0.10
    noch
    0.10
    à¸IJาà¸Ļ
    0.10
    UNE
    0.09
    une
    0.09
    èµ°
    0.09
    ÑĥÑĩа
    0.09
    Activations Density 0.081%

    No Known Activations