© 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. 47686
    Prev
    Next
    INDEX
    Explanations

    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
    åĬĽåº¦
    -0.11
    çľĭå®Į
    -0.10
    .CopyTo
    -0.10
    ä¿Ŀå®Ī
    -0.10
    _None
    -0.09
    اص
    -0.09
    ç¿
    -0.09
    udas
    -0.08
    sov
    -0.08
    éĺħè§Ī
    -0.08
    POSITIVE LOGITS
    幸ç¦ı
    0.25
     happiness
    0.20
    幸ç¦ıæĦŁ
    0.18
    å¿«ä¹IJ
    0.17
     Happiness
    0.17
    å¿«æ¨Ĥ
    0.14
    happy
    0.13
     happy
    0.13
    幸ãģĽ
    0.13
     happier
    0.13
    Activations Density 0.054%

    No Known Activations