© 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. 24316
    Prev
    Next
    INDEX
    Explanations

    said after conjunctions

    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
    hausen
    -0.10
    æľ¬æľŁ
    -0.09
    ardi
    -0.09
    BUFF
    -0.09
    aina
    -0.09
    istani
    -0.09
    åİĨæĿ¥
    -0.09
    æ¯ıå¹´
    -0.09
    piel
    -0.09
    inus
    -0.08
    POSITIVE LOGITS
    abouts
    0.09
    侪
    0.09
    åĬ¿å¤´
    0.09
    èĤ©è´Ł
    0.09
    骤
    0.08
    åĨ²åĩ»
    0.08
    åħ¨æł¡
    0.08
    æĸ°æ¬¾
    0.08
    ä¼ļä¸Ĭ
    0.08
    ego
    0.08
    Activations Density 0.158%

    No Known Activations