© 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. 58053
    Prev
    Next
    INDEX
    Explanations

    secondary/high/primary school

    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
    MLS
    -0.10
    вез
    -0.09
    å®ŀäºĭ
    -0.09
    å¿Ŀ
    -0.08
    (Gravity
    -0.08
     ÑģÑĤоим
    -0.08
    祧
    -0.08
    elf
    -0.08
    åı«å£°
    -0.08
    æĸ¯åŁº
    -0.08
    POSITIVE LOGITS
    éĻ¢æł¡
    0.13
    èĸª
    0.10
    åŃ¦æł¡
    0.09
    éĴį
    0.09
    éĺ´è°ĭ
    0.08
     school
    0.08
    andes
    0.08
     phá»ķ
    0.08
    åijķ
    0.08
    æĪ´ä¸Ĭ
    0.08
    Activations Density 0.078%

    No Known Activations