© 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. 6198
    Prev
    Next
    INDEX
    Explanations

    craft

    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
    oader
    -0.10
    ents
    -0.10
    泫
    -0.10
    Ñģ
    -0.10
    å¾Ĺèµ·
    -0.09
    overe
    -0.09
    -priced
    -0.09
     ÑģамÑĭм
    -0.09
    éķ¿è¾Ī
    -0.09
    ision
    -0.09
    POSITIVE LOGITS
    fully
    0.13
    eur
    0.11
    ree
    0.10
    ually
    0.09
    asan
    0.09
    ools
    0.09
    ught
    0.09
    wright
    0.09
    rial
    0.09
    ãģĤãĤĭ
    0.09
    Activations Density 0.017%

    No Known Activations