© 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. 12167
    Prev
    Next
    INDEX
    Explanations

    preventive measures

    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
    çĦ¶æĺ¯
    -0.10
    iers
    -0.10
    æĥij
    -0.09
    殿ä¸ĭ
    -0.09
    shire
    -0.09
    oma
    -0.09
    é¦ģ
    -0.09
    Ùħا
    -0.09
    yer
    -0.08
    омÑĥ
    -0.08
    POSITIVE LOGITS
    UREMENT
    0.10
     пÑĢедоÑģÑĤ
    0.10
    ments
    0.10
    edImage
    0.09
    edList
    0.09
    aters
    0.09
    æݪæĸ½
    0.09
    TURE
    0.09
    çĺķ
    0.09
    antly
    0.09
    Activations Density 0.025%

    No Known Activations