© 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. 40039
    Prev
    Next
    INDEX
    Explanations

    college

    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
    åħĢ
    -0.10
    ç¬ı
    -0.10
    身边
    -0.10
    身éĤĬ
    -0.09
    åĪ¹
    -0.09
    缦
    -0.09
    身边çļĦ
    -0.09
    pile
    -0.08
    æ¯Ķäºļ
    -0.08
    coh
    -0.08
    POSITIVE LOGITS
    çĶ¨åľ°
    0.11
    ensed
    0.09
    zens
    0.09
    ãģĮãĤī
    0.09
    /ne
    0.09
    éĩĮçļĦ
    0.09
    èĢģ大
    0.09
    æĽ°
    0.08
    zen
    0.08
    æľ¬ç§ijçĶŁ
    0.08
    Activations Density 0.009%

    No Known Activations