© 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. 29418
    Prev
    Next
    INDEX
    Explanations

    hierarchy and hierarchical structures

    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
    ¿
    -0.10
    deer
    -0.10
    AtPath
    -0.09
    rock
    -0.08
    ctors
    -0.08
    ld
    -0.08
     üst
    -0.08
    çĵ¯
    -0.08
    éĨĽ
    -0.08
    utor
    -0.08
    POSITIVE LOGITS
    .levels
    0.11
    å¾Īæ¸ħæ¥ļ
    0.10
    amon
    0.10
    onym
    0.09
    تÙħ
    0.09
    -addon
    0.09
    鸽
    0.09
    .cv
    0.08
    archical
    0.08
    ester
    0.08
    Activations Density 0.023%

    No Known Activations