© 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. 686
    Prev
    Next
    INDEX
    Explanations

    hardware and construction components

    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
    .ERR
    -0.11
    宫
    -0.10
    ç®Ń
    -0.10
    æķ´è½¦
    -0.09
    .editor
    -0.09
    彬
    -0.09
    owo
    -0.08
    oka
    -0.08
    幸
    -0.08
    darwin
    -0.08
    POSITIVE LOGITS
    èŀºä¸Ŀ
    0.10
    è´´
    0.09
    Fcn
    0.08
     Hoch
    0.08
    éĥ½èĥ½å¤Ł
    0.08
    æݨ广
    0.08
     limiting
    0.08
     Cure
    0.08
    çĽ²
    0.08
     Staples
    0.08
    Activations Density 0.116%

    No Known Activations