© 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. 785
    Prev
    Next
    INDEX
    Explanations

    root directory

    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
    à¸ĵ
    -0.10
    rier
    -0.10
    åijĺ
    -0.09
    å¾Ĺèµ·
    -0.09
    nist
    -0.09
    apo
    -0.09
    tron
    -0.09
    ons
    -0.08
    encing
    -0.08
    encer
    -0.08
    POSITIVE LOGITS
    æ¤IJ
    0.14
    kits
    0.13
    æŁ¢
    0.13
    less
    0.11
    strap
    0.11
    åĵĩ
    0.11
    ãģ£ãģĵ
    0.10
    beer
    0.09
    лов
    0.09
     chic
    0.09
    Activations Density 0.052%

    No Known Activations