© 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. 11208
    Prev
    Next
    INDEX
    Explanations

    death or deceased

    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
    äºĮæľŁ
    -0.10
    é£İåIJ¹
    -0.10
    æĹı群
    -0.09
    éģĹå¿ĺ
    -0.09
    ä¸ĢæľŁ
    -0.09
    eras
    -0.09
    çļĦæ¯į亲
    -0.09
    ist
    -0.09
    ãģ¨ãĤĬ
    -0.08
    è¯Ŀè¯Ń
    -0.08
    POSITIVE LOGITS
    -fashioned
    0.08
    vertise
    0.08
    ste
    0.08
    roe
    0.08
    room
    0.08
    ward
    0.08
    rence
    0.08
     McM
    0.08
     Vinci
    0.08
    ::_('
    0.07
    Activations Density 0.016%

    No Known Activations