© 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. 5975
    Prev
    Next
    INDEX
    Explanations

    encryption / decryption

    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
    ernel
    -0.10
    uez
    -0.08
     ë¬¼ë¡ł
    -0.08
    elves
    -0.08
    ICENSE
    -0.08
    lessly
    -0.08
    allas
    -0.08
    ñe
    -0.07
     $($
    -0.07
    vironment
    -0.07
    POSITIVE LOGITS
    /etc
    0.12
     <![
    0.10
    ctrine
    0.10
    ËĪ
    0.10
    å±ij
    0.08
    åIJĦ家
    0.08
    è¹Ī
    0.08
    phans
    0.08
    ãģĤãĤĭãģĦ
    0.08
    ategy
    0.08
    Activations Density 0.460%

    No Known Activations