© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 18718
    Prev
    Next
    INDEX
    Explanations

    suicide and death

    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
    巨人
    -0.10
    PD
    -0.08
    วà¸Ķ
    -0.08
    ocked
    -0.08
     backed
    -0.08
    ç»ĦåIJĪ
    -0.08
    èĶ¼
    -0.08
    /fl
    -0.08
     ráp
    -0.08
     PD
    -0.08
    POSITIVE LOGITS
    èĩªæĿĢ
    0.15
    æĬĬèĩªå·±
    0.15
    æ®ī
    0.13
    念头
    0.12
    æŃ»
    0.12
    æĬĬèĩªå·±çļĦ
    0.12
    æŃ»äº¡
    0.12
    å±ŀäºİèĩªå·±
    0.12
     suicide
    0.11
    为èĩªå·±
    0.11
    Activations Density 0.052%

    No Known Activations