© 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. 33242
    Prev
    Next
    INDEX
    Explanations

    microplastics, coextrusion, plast

    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
     Diss
    -0.10
     Buckley
    -0.09
     diss
    -0.09
    æ°´çĶµ
    -0.09
    ç«ĭéĿ¢
    -0.09
     Bol
    -0.08
    çķı
    -0.08
    atform
    -0.08
    è¦ĨçĽĸçİĩ
    -0.08
    vrier
    -0.08
    POSITIVE LOGITS
    寰
    0.09
    æĬĵ
    0.09
    åIJ¹
    0.09
    empor
    0.09
    æīª
    0.09
    çĵ¶
    0.08
    çĵ¶åŃIJ
    0.08
    äºĴèģĶäºĴéĢļ
    0.08
    å¡ijæĸĻ
    0.08
    oplast
    0.08
    Activations Density 0.112%

    No Known Activations