© 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. 40428
    Prev
    Next
    INDEX
    Explanations

    of the

    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
    åĿij
    -0.09
    éļIJéļIJ
    -0.09
    älle
    -0.08
    jective
    -0.08
    åĪ°æŶåĢĻ
    -0.08
    ãĥ¼ãĥ³
    -0.08
    åIJĥæĥĬ
    -0.08
    æŃ¢
    -0.08
     Ñĩелов
    -0.08
    awy
    -0.08
    POSITIVE LOGITS
    侨
    0.08
    æĶ¿åºľéĩĩè´Ń
    0.08
    own
    0.08
    éº
    0.08
     Mey
    0.08
     ÑĩаÑģ
    0.08
    è¿Ļ段
    0.08
    åŨ
    0.08
    åĽ½éĻħå¸Ĥåľº
    0.08
     cst
    0.08
    Activations Density 0.001%

    No Known Activations