© 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. 60858
    Prev
    Next
    INDEX
    Explanations

    prior to

    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
    纱
    -0.09
    çĦī
    -0.09
    à®´
    -0.09
    çħ¦
    -0.08
     LAW
    -0.08
    rose
    -0.08
    èĩ³å°ij
    -0.08
    .icons
    -0.08
    -best
    -0.08
    shire
    -0.08
    POSITIVE LOGITS
    碧
    0.09
    preced
    0.09
     Morales
    0.09
    è©
    0.09
    æľīè¿Ļæł·çļĦ
    0.09
    æĭĤ
    0.08
    æłĹ
    0.08
    æŶåĢĻ
    0.08
    åħĪ
    0.08
    éĻIJ
    0.08
    Activations Density 0.016%

    No Known Activations