© 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. 728
    Prev
    Next
    INDEX
    Explanations

    offer or provide

    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
    éĴ¢æĿIJ
    -0.11
    ạt
    -0.10
    ç»ĻåŃ©åŃIJ
    -0.10
    æŃ£æĸĩ
    -0.10
    amon
    -0.09
    aho
    -0.09
    ç»Ħå§Ķä¼ļ
    -0.09
    Ðģ
    -0.09
     hum
    -0.09
    å°Ŀ
    -0.09
    POSITIVE LOGITS
     Lau
    0.09
    äºĨ许å¤ļ
    0.09
    æľīåIJįçļĦ
    0.08
    åĽĽç§į
    0.08
    éĿŀ常å¤ļçļĦ
    0.08
    çŃij
    0.08
    æĢĸ
    0.08
    NEL
    0.08
    NIL
    0.08
    éĿŀ常好çļĦ
    0.08
    Activations Density 0.035%

    No Known Activations