© 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. 687
    Prev
    Next
    INDEX
    Explanations

    repeat, repetition, repeated

    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
    alent
    -0.11
    ÑģÑĭл
    -0.10
    æĬĬèĩªå·±çļĦ
    -0.09
    (argument
    -0.09
    æĸ°çļĦä¸Ģ
    -0.09
    .microsoft
    -0.08
    éŀĺ
    -0.08
    ìļķ
    -0.08
    ä¸Ģå¹ħ
    -0.08
    athe
    -0.08
    POSITIVE LOGITS
    äºĨä¸Ģéģį
    0.11
    产ä¸ļåŁºåľ°
    0.09
    iators
    0.09
     ×Ķ×ŀ׼
    0.09
    ken
    0.09
    æĿIJè´¨
    0.09
    è¡ĮæĶ¿éĥ¨éŨ
    0.08
    roe
    0.08
    iad
    0.08
    zas
    0.08
    Activations Density 0.005%

    No Known Activations