© 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. 3117
    Prev
    Next
    INDEX
    Explanations

    served on the board

    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
    ilty
    -0.09
    翳
    -0.09
    èµ°è¿ĩ
    -0.09
    涨
    -0.09
    辩
    -0.08
    æ²Ļé¾Ļ
    -0.08
     Lal
    -0.08
    ayo
    -0.08
    ussion
    -0.08
    å½±
    -0.08
    POSITIVE LOGITS
    åħij
    0.10
    ãģ¼
    0.09
    caler
    0.09
    åīIJ
    0.09
    åıijçĶŁåľ¨
    0.08
    CADE
    0.08
    cale
    0.08
    读èĢħ
    0.08
    /download
    0.08
    éķ«
    0.08
    Activations Density 0.016%

    No Known Activations