© 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. 40129
    Prev
    Next
    INDEX
    Explanations

    self-esteem and negative emotions

    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
     saf
    -0.09
    ä¾ĽéľĢ
    -0.09
    æĹłçŁ¥
    -0.09
    åĻ±
    -0.08
    çĮİ
    -0.08
    åij¼åºĶ
    -0.08
    atri
    -0.08
    éľ²
    -0.08
     expos
    -0.08
    _SAFE
    -0.08
    POSITIVE LOGITS
    æĬĬèĩªå·±
    0.10
    è§īå¾Ĺèĩªå·±
    0.10
    çŃĿ
    0.10
     Shame
    0.10
     guilt
    0.10
    æĬ±æŃī
    0.09
    èĢ¿
    0.09
    åĽŀ头
    0.09
    à¹īà¸ĩ
    0.09
    öl
    0.09
    Activations Density 0.041%

    No Known Activations