© 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. 40353
    Prev
    Next
    INDEX
    Explanations

    C++ template headers

    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
    ives
    -0.11
    oret
    -0.10
    大家ä¸Ģèµ·
    -0.10
    æľīæķĪæľŁ
    -0.09
     hamm
    -0.09
    ç¾İèªī
    -0.09
    ander
    -0.09
    pped
    -0.09
    æĪIJåijĺåįķä½į
    -0.08
    å±Ģéķ¿
    -0.08
    POSITIVE LOGITS
    åľŃ
    0.09
    filt
    0.09
    edition
    0.09
    aceous
    0.08
    -trained
    0.08
     Guild
    0.08
    /vector
    0.08
    itas
    0.08
    aginator
    0.08
    Edition
    0.08
    Activations Density 0.089%

    No Known Activations