© 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. 60574
    Prev
    Next
    INDEX
    Explanations

    place names ending in burg/ando/county/ridge

    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
    ffer
    -0.09
    asar
    -0.09
    ÑĩиÑģлен
    -0.09
    æľ¬äºº
    -0.08
    eur
    -0.08
    ctions
    -0.08
    伦
    -0.08
    vinces
    -0.08
    hog
    -0.08
    Clip
    -0.08
    POSITIVE LOGITS
    å±ŀå®ŀ
    0.10
    åħħåĪĨåıijæĮ¥
    0.09
    好å¤ļ
    0.09
    çİĭçīĮ
    0.08
    åĥĸ
    0.08
    è¢ħ
    0.08
    çĮ©
    0.08
    èĮ¸
    0.08
    BOR
    0.08
    á»ķi
    0.08
    Activations Density 0.011%

    No Known Activations