© 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. 5560
    Prev
    Next
    INDEX
    Explanations

    place names ending in -ton, -ley, -oria, -abad, -lia

    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
    桧
    -0.10
    éĿ¡
    -0.09
    /interface
    -0.09
    æŃī
    -0.08
    没è§ģè¿ĩ
    -0.08
    é¢į
    -0.08
    ical
    -0.08
    äºĨèĩªå·±çļĦ
    -0.08
    eteria
    -0.08
    ught
    -0.08
    POSITIVE LOGITS
    è²Į
    0.10
    asto
    0.10
     ÑģвÑıзи
    0.09
    ate
    0.09
    -sized
    0.09
    ties
    0.08
    ä¼ļåIJĮ
    0.08
    orian
    0.08
    asti
    0.08
    istas
    0.08
    Activations Density 0.003%

    No Known Activations