© 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. 29479
    Prev
    Next
    INDEX
    Explanations

    ant sports

    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
    ä¹İ
    -0.12
    åı£æ°Ķ
    -0.11
    wards
    -0.10
    好å¤ļ
    -0.10
    çĿ¦
    -0.09
     Ñģобой
    -0.09
    æĪĸå¤ļ
    -0.09
    ANEL
    -0.08
    uong
    -0.08
    åĴİ
    -0.08
    POSITIVE LOGITS
    è··
    0.09
    ä¸Ģ举
    0.08
    æĢĻ
    0.08
    ä¸Ģå¹ķ
    0.08
    åĭĥåĭĥ
    0.07
    çħ¦
    0.07
    virt
    0.07
    /her
    0.07
    pkg
    0.07
     Globe
    0.07
    Activations Density 1.576%

    No Known Activations