© 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. 26797
    Prev
    Next
    INDEX
    Explanations

    ballads, hymns, odes, songs

    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
    ousse
    -0.10
    åī¯
    -0.10
    å¤ļç§įå½¢å¼ı
    -0.09
    amen
    -0.09
    ç»ŀ
    -0.09
    ormsg
    -0.09
    overs
    -0.08
    _goods
    -0.08
    ava
    -0.08
    asket
    -0.08
    POSITIVE LOGITS
    é«ĺæĺĤ
    0.10
    -library
    0.10
    ãĤªãĥ³
    0.10
    åĴı
    0.10
    ä¿Ŀä¿®
    0.10
    åĸĿäºĨ
    0.10
    æĮ½åĽŀ
    0.09
    ocks
    0.09
    ãģ¾ãģ¾
    0.09
    enal
    0.09
    Activations Density 0.026%

    No Known Activations