© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38613
    Prev
    Next
    INDEX
    Explanations

    recently, today, yet, now

    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
    igor
    -0.10
    .sam
    -0.09
    .Flat
    -0.09
    æľīæľº
    -0.09
    .dm
    -0.09
    olk
    -0.09
    (dm
    -0.08
    곡
    -0.08
    anka
    -0.08
    syscall
    -0.08
    POSITIVE LOGITS
     rằng
    0.13
     whether
    0.12
     bahwa
    0.10
    æĺ¯åIJ¦æľī
    0.10
     how
    0.10
     that
    0.10
     Ø£ÙĨÙĩ
    0.10
    çī¹åĪ«æĺ¯
    0.09
    æĺ¯åIJ¦åŃĺåľ¨
    0.09
     Ø£ÙĨ
    0.09
    Activations Density 0.047%

    No Known Activations