© 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. 51785
    Prev
    Next
    INDEX
    Explanations

    firmware version or BIOS

    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
    æĽ´å¤ļçļĦ
    -0.08
    æĴĩ
    -0.08
    .Generated
    -0.08
    èįª
    -0.08
    sth
    -0.08
    åĬ¡
    -0.08
    ter
    -0.08
    äu
    -0.08
    pix
    -0.08
    .BackgroundImage
    -0.08
    POSITIVE LOGITS
    件
    0.09
    æĢ¯
    0.09
    èij«
    0.08
    æľŁ
    0.08
    ached
    0.08
    ep
    0.08
    acas
    0.08
    .amazon
    0.08
     Belmont
    0.08
     днÑı
    0.08
    Activations Density 0.015%

    No Known Activations