© 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. 16604
    Prev
    Next
    INDEX
    Explanations

    waste of time, money, resources

    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
     Ñģли
    -0.10
     completo
    -0.09
    人士
    -0.09
    ä¸įéĢĤ
    -0.09
    ssel
    -0.09
    缺失
    -0.09
    _EXTENDED
    -0.09
    ury
    -0.08
    ssa
    -0.08
    ä¸įå®ī
    -0.08
    POSITIVE LOGITS
    fully
    0.17
    ful
    0.10
    åĬĽæ°Ķ
    0.09
    èģĮæĿĥ
    0.09
    omer
    0.08
    æİī
    0.08
    _EXPECT
    0.08
    ream
    0.08
     Pret
    0.08
    黾
    0.08
    Activations Density 0.008%

    No Known Activations