© 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. 36070
    Prev
    Next
    INDEX
    Explanations

    Interface, MBA, America, INC., CO

    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
     Ñĩа
    -0.09
    åįıä¼ļä¼ļéķ¿
    -0.09
     Fir
    -0.08
    riere
    -0.08
    ãĤĴè¦ĭãĤĭ
    -0.08
    alex
    -0.08
    ondon
    -0.08
     ÑģвÑıзан
    -0.08
    iant
    -0.08
    å®ĿçŁ³
    -0.08
    POSITIVE LOGITS
    ä¸ĭå±ŀ
    0.10
    æĹĹä¸ĭ
    0.10
    æĹĹä¸ĭçļĦ
    0.10
    æįŁ
    0.09
    åįļæĸĩ
    0.09
    ä¸Ģ件
    0.09
    åħ¬åı¸çļĦ
    0.09
    çļĦåIJįåŃĹ
    0.08
    inya
    0.08
    isci
    0.08
    Activations Density 0.043%

    No Known Activations