© 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. 3069
    Prev
    Next
    INDEX
    Explanations

    congratulations and happiness

    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
    Not in Any Lists

    No Comments

    Negative Logits
    acja
    -0.10
    avan
    -0.09
    çĽĶ
    -0.09
    æ¼ı
    -0.09
    ntag
    -0.09
    å´¤
    -0.09
    .ov
    -0.09
     Simmons
    -0.09
    çī¢
    -0.09
     Ivy
    -0.08
    POSITIVE LOGITS
    ç¥Ŀè´º
    0.25
    ç¥Ŀç¦ı
    0.24
    ç¥Ŀ
    0.19
    ç¥ĿæĦ¿
    0.18
    è´º
    0.17
    æģŃåĸľ
    0.17
     congrat
    0.17
    åºĨ
    0.12
    Congratulations
    0.12
    åĶģ
    0.12
    Activations Density 0.065%

    No Known Activations