© 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. 7995
    Prev
    Next
    INDEX
    Explanations

    WikiLeaks and Assange activities

    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
    éģĵè·¯
    -0.09
    วร
    -0.09
    é¢Ħç®Ĺ
    -0.09
    åĢŃ
    -0.09
    립
    -0.09
    ugen
    -0.09
     дизайн
    -0.08
    _unpack
    -0.08
    å¡Į
    -0.08
    )[-
    -0.08
    POSITIVE LOGITS
     Assange
    0.10
     WikiLeaks
    0.09
    è¿Ħä»Ĭ
    0.09
    ozy
    0.09
    裸
    0.08
    ç½ijç«Ļ建设
    0.08
    ç¥ŀåĻ¨
    0.08
    jon
    0.08
    3
    0.08
     surf
    0.08
    Activations Density 0.027%

    No Known Activations