© 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. 29740
    Prev
    Next
    INDEX
    Explanations

    death and mortality related prefixes

    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
    ãģĤãĤĬãģ¾ãģĻãģĮ
    -0.11
    ãģĤãĤĬãģ¾ãģĻ
    -0.10
     дела
    -0.10
    anon
    -0.09
    iring
    -0.09
    oard
    -0.09
    ìĤ¬íķŃ
    -0.09
    æīĢæľī人éĥ½
    -0.08
    æ¿ī
    -0.08
    å§Ķ书记
    -0.08
    POSITIVE LOGITS
    oked
    0.09
    ISTIC
    0.08
    -quarters
    0.08
    åIJĥä»Ģä¹Ī
    0.08
    åĴĮåľ°åĮº
    0.08
    -song
    0.08
    ominated
    0.08
    ãģ¡ãģª
    0.08
    ryption
    0.08
    ĵ
    0.08
    Activations Density 0.221%

    No Known Activations