© 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. 855
    Prev
    Next
    INDEX
    Explanations

    allowances, allow me, allow script

    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
    çĦ¶æĺ¯
    -0.10
    好åIJĹ
    -0.10
    å§Ķ
    -0.10
    eker
    -0.10
    棵
    -0.09
    ä¹ı
    -0.09
    主宰
    -0.09
    éĵ¼
    -0.09
    é¾Ħ
    -0.09
    ç¥Ł
    -0.09
    POSITIVE LOGITS
    ments
    0.09
    umb
    0.09
    ington
    0.09
    nowled
    0.09
    ÙģØ©
    0.09
    ment
    0.08
     Lug
    0.08
    anter
    0.08
    ably
    0.08
    stm
    0.08
    Activations Density 0.035%

    No Known Activations