© 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. 16816
    Prev
    Next
    INDEX
    Explanations

    rear of vehicles or locations

    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
    ãĤĪãģĨãģ«
    -0.13
    adel
    -0.11
    iating
    -0.10
    ippers
    -0.10
    ipped
    -0.10
     تعاÙĦÙī
    -0.10
    ting
    -0.09
    elsen
    -0.09
    ãģĵãģ¨
    -0.09
    oter
    -0.09
    POSITIVE LOGITS
    -most
    0.15
    ward
    0.14
    wards
    0.12
    most
    0.12
    loom
    0.10
    WARDS
    0.10
    LOB
    0.10
    mente
    0.10
    å¾Ĺä½ı
    0.10
    lings
    0.10
    Activations Density 0.015%

    No Known Activations