© 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. 48090
    Prev
    Next
    INDEX
    Explanations

    outperforming competitors, outselling others

    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
    çľ¼è§Ĵ
    -0.10
    èĢĮéĿŀ
    -0.10
    åĢ®
    -0.09
    çIJ°
    -0.09
    ä¹Łå¥½
    -0.09
    åıĮèĦļ
    -0.09
    ä¸įåIJĮäºİ
    -0.09
    é£İåIJ¹
    -0.09
    å²·
    -0.09
    çŃ·
    -0.09
    POSITIVE LOGITS
    ç«ŀäºī对æīĭ
    0.10
    åIJĮç±»
    0.09
     counterpart
    0.09
    åIJĮçŃī
    0.09
     counterparts
    0.09
    /cs
    0.08
     competing
    0.08
    inx
    0.08
    aska
    0.08
    antium
    0.08
    Activations Density 0.072%

    No Known Activations