© 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. 12411
    Prev
    Next
    INDEX
    Explanations

    something else

    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
    çļĦä¸Ģ大
    -0.11
    æķ¬ä¸ļ
    -0.09
    4
    -0.08
    7
    -0.08
     sentiments
    -0.08
    onas
    -0.08
    å¾Ī大ç¨ĭ度
    -0.08
    éĤ£ä¹Īå¤ļ
    -0.08
     excess
    -0.08
    å¥
    -0.08
    POSITIVE LOGITS
    æŁIJç§į
    0.11
     alguna
    0.10
    åħ¶ä»ĸçļĦ
    0.09
    çī¹æ®ĬçļĦ
    0.09
    éri
    0.09
    _cipher
    0.09
     Forbidden
    0.09
    å±±åºĦ
    0.09
    kees
    0.09
    .initializeApp
    0.09
    Activations Density 0.098%

    No Known Activations