© 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. 5983
    Prev
    Next
    INDEX
    Explanations

    Spanish and Portuguese names and places

    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
    楫
    -0.10
    éĿĪ
    -0.09
    èĤĮèĤ¤
    -0.09
    çľ¼åħī
    -0.09
    çģµ
    -0.09
    éĢ¶
    -0.09
    æŶæŶ
    -0.09
    iali
    -0.09
     Luigi
    -0.08
    æĶ¾åģĩ
    -0.08
    POSITIVE LOGITS
    å·´æĸ¯
    0.09
    çĮº
    0.09
     Chill
    0.09
    ped
    0.09
     Penal
    0.09
     Vas
    0.08
    å°ĸ
    0.08
    .esp
    0.08
    çļĦ身份
    0.08
     Belmont
    0.08
    Activations Density 0.086%

    No Known Activations