© 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. 47600
    Prev
    Next
    INDEX
    Explanations

    suicide

    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
    çĸ£
    -0.10
    åĪĨå±Ģ
    -0.09
    ç¿©
    -0.09
    èĨº
    -0.09
    pto
    -0.09
    æ¦Ĥ
    -0.08
    å§ĭç»Īä¿ĿæĮģ
    -0.08
    åIJĮå¿ĥ
    -0.08
    illian
    -0.08
    å¿ĥå¾Ĺ
    -0.08
    POSITIVE LOGITS
    èĩªæĿĢ
    0.11
    念头
    0.11
    å¥ļ
    0.10
    æ·ħ
    0.10
     suicide
    0.10
     suicidal
    0.10
    åįľ
    0.09
    èĿ¼
    0.09
     Suicide
    0.09
     resolving
    0.09
    Activations Density 0.067%

    No Known Activations