© 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. 1588
    Prev
    Next
    INDEX
    Explanations

    death and

    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
    åŃIJéĩĮ
    -0.10
     пÑĥ
    -0.10
    éķĹ
    -0.10
     Bew
    -0.09
    æIJª
    -0.09
    æ±Łæ·®
    -0.09
    èĭĩ
    -0.09
    jeta
    -0.09
    orth
    -0.09
    PRI
    -0.09
    POSITIVE LOGITS
    ened
    0.09
    åĬŁèĥ½æĢ§
    0.09
    æŃ»
    0.09
     ÙĪاÙĦÙģ
    0.09
    fully
    0.09
    mium
    0.09
    åĽŀåĪ°å®¶
    0.08
    (dead
    0.08
     Death
    0.08
    working
    0.08
    Activations Density 0.022%

    No Known Activations