© 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. 24187
    Prev
    Next
    INDEX
    Explanations

    digital downloads

    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
     Cav
    -0.09
    æŀļ
    -0.09
    åī¥
    -0.09
     Lor
    -0.09
     büt
    -0.09
    untu
    -0.08
    åıĺæĢģ
    -0.08
     HoÃłng
    -0.08
    æİ°
    -0.08
    plier
    -0.08
    POSITIVE LOGITS
    argo
    0.10
    _FAULT
    0.10
    ont
    0.09
    uro
    0.09
    é¦ĸ
    0.09
    alley
    0.08
    oured
    0.08
    è¿Ļä¸Ģå¹´
    0.08
    ieres
    0.08
    /stream
    0.08
    Activations Density 0.018%

    No Known Activations