© 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. 40216
    Prev
    Next
    INDEX
    Explanations

    dates and berries

    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
    转身
    -0.10
    missive
    -0.09
    å°¸
    -0.09
    protocol
    -0.09
     Dane
    -0.09
    èĪįä¸įå¾Ĺ
    -0.09
    åŃĺ
    -0.09
    å±ŀ
    -0.08
    éĻ©
    -0.08
    Extensions
    -0.08
    POSITIVE LOGITS
    æŀ£
    0.10
    iba
    0.09
    åľ°æĸ¹
    0.09
     rais
    0.09
    éķ¿å¤§
    0.08
    çĭ¬
    0.08
    éªĿ
    0.08
     deb
    0.08
     Laden
    0.08
    裹
    0.08
    Activations Density 0.057%

    No Known Activations