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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21197
    Prev
    Next
    INDEX
    Explanations

    selfishness, narcissism, greed, self-interest

    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
    woord
    -0.10
     BRE
    -0.10
    adio
    -0.09
    lore
    -0.09
    èĪµ
    -0.09
    åħµåĻ¨
    -0.09
    راÙĤ
    -0.09
    çªģ
    -0.09
    è¿Ń
    -0.09
     lookahead
    -0.09
    POSITIVE LOGITS
    ä¾Ħ
    0.08
    å°ıåŃIJ
    0.08
    é¢ĺæĿIJ
    0.08
    æİıåĩº
    0.08
    éĽķ
    0.08
    ä¸ĸ代
    0.08
    --------------------------------------------------------------------------↵
    0.08
     Nik
    0.08
    è°İ
    0.08
    åł¡
    0.08
    Activations Density 0.027%

    No Known Activations