© 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. 63740
    Prev
    Next
    INDEX
    Explanations

    Portuguese prepositions

    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
     same
    -0.12
    oretical
    -0.10
     пÑĢÑı
    -0.10
    ed
    -0.09
    same
    -0.09
    day
    -0.08
    евÑĭе
    -0.08
    åĻ±
    -0.08
    .same
    -0.08
    Same
    -0.08
    POSITIVE LOGITS
    çļĦä¸ĢåĪĩ
    0.11
    åıijå±ķä¸Ń
    0.10
    åħ·ä½ĵçļĦ
    0.10
    åĵ¡
    0.10
    ä¸Ģ对
    0.10
    æĶ¯æĮģ
    0.10
    æ±ķ
    0.09
    igte
    0.09
    resse
    0.09
    屿
    0.09
    Activations Density 0.031%

    No Known Activations