© 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. 63845
    Prev
    Next
    INDEX
    Explanations

    highlands and land

    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
    大æĪ·
    -0.09
    æĻļé¥Ń
    -0.09
    ãĤ£
    -0.09
    PRI
    -0.09
    ismatic
    -0.08
    Laugh
    -0.08
    ä¸įæ¸ħ
    -0.08
    SED
    -0.08
    åįĩåѦ
    -0.08
    åħ®
    -0.08
    POSITIVE LOGITS
     ÑģебÑı
    0.10
    enburg
    0.10
    onso
    0.10
    enan
    0.10
    ierge
    0.10
    омеÑĢ
    0.09
     rid
    0.09
    sWith
    0.09
    eur
    0.09
    orado
    0.09
    Activations Density 0.009%

    No Known Activations