© 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. 29488
    Prev
    Next
    INDEX
    Explanations

    world-wide-web

    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
    uropean
    -0.10
    ä¸įæĸŃåľ°
    -0.10
    åĩ³
    -0.10
    chy
    -0.10
    å¯Įè´µ
    -0.09
    äºĨä¸Ģ个
    -0.09
    åĨįå¤ļ
    -0.09
    oooooooo
    -0.09
    lessly
    -0.09
    lobal
    -0.08
    POSITIVE LOGITS
    /-
    0.20
    sonian
    0.13
    ftware
    0.13
    gether
    0.13
    ysics
    0.13
    odore
    0.12
    acters
    0.12
    orary
    0.11
    ÑįÑĤомÑĥ
    0.11
    entication
    0.11
    Activations Density 2.199%

    No Known Activations