© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7372
    Prev
    Next
    INDEX
    Explanations

    Professor of

    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
    _BROWSER
    -0.09
    伦
    -0.08
    让人们
    -0.08
    ä¿Ĺ
    -0.08
    ä¸įäºĨ
    -0.08
    /rs
    -0.08
    à¹Ģย
    -0.08
    lers
    -0.08
    den
    -0.08
    大楼
    -0.08
    POSITIVE LOGITS
     Ñĥме
    0.11
    idon
    0.09
    _DUMP
    0.09
     Nunes
    0.09
    åĿIJèIJ½åľ¨
    0.09
    IJľ
    0.09
    åIJĦéĥ¨éŨ
    0.09
    anax
    0.08
    undry
    0.08
    ourg
    0.08
    Activations Density 0.032%

    No Known Activations