© 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. 16571
    Prev
    Next
    INDEX
    Explanations

    homo- prefix

    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
    Negative Logits
    atten
    -0.10
    à¸Ĺรà¸ĩ
    -0.10
    åIJĮåŁİ
    -0.10
    velopment
    -0.10
    throp
    -0.09
    ingly
    -0.09
    pery
    -0.09
    ê¸Ī
    -0.09
     hÆ°á»Łng
    -0.09
    HING
    -0.09
    POSITIVE LOGITS
    æĢ§å¼º
    0.10
    åĮĸçļĦ
    0.10
    mercial
    0.10
    å±ī
    0.10
    iliar
    0.10
    ality
    0.09
    estruct
    0.09
    ulate
    0.09
    鸽
    0.09
    eking
    0.08
    Activations Density 0.030%

    No Known Activations