© 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. 24269
    Prev
    Next
    INDEX
    Explanations

    car and vehicle details

    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
    éĺħ读åħ¨æĸĩ
    -0.09
    å·¡
    -0.09
    人éĢł
    -0.08
    éĩįè¦ģåİŁåĽł
    -0.08
    åĪĨåī²
    -0.08
    æµ·æ°´
    -0.08
    åĪ·åį¡
    -0.08
    èħ®
    -0.08
    end
    -0.08
     Beginners
    -0.08
    POSITIVE LOGITS
    çļ®
    0.12
    lesh
    0.10
     cars
    0.09
     FRONT
    0.09
    .soft
    0.08
    è®´
    0.08
    饰
    0.08
    çĨĦ
    0.08
    æķŀ
    0.08
    Transmission
    0.08
    Activations Density 0.187%

    No Known Activations