© 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. 24253
    Prev
    Next
    INDEX
    Explanations

    psych- words/suffixes

    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
    åŃIJéĩĮ
    -0.10
    inton
    -0.10
    -handed
    -0.09
    åĨ³å¿ĥ
    -0.09
    owing
    -0.09
     pauses
    -0.09
     phá»ij
    -0.09
    eted
    -0.09
    hip
    -0.08
    chaft
    -0.08
    POSITIVE LOGITS
    MBOL
    0.10
    ters
    0.10
    lopedia
    0.10
    onaut
    0.10
    ors
    0.09
    elong
    0.09
    fully
    0.09
     ÙĪاÙĦع
    0.09
    ALLY
    0.09
     minded
    0.09
    Activations Density 0.034%

    No Known Activations