© 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. 30229
    Prev
    Next
    INDEX
    Explanations

    Planet followed by web, .com, show, key, Smash

    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
    éĴĿ
    -0.09
    ä¾ĭè¡Į
    -0.09
     Bos
    -0.08
    åľ¨ä»ĸ
    -0.08
    aldo
    -0.08
    iaux
    -0.08
    entication
    -0.08
    oses
    -0.08
    åľ¨åIJĮä¸Ģ
    -0.08
    ium
    -0.08
    POSITIVE LOGITS
    ä¸įåĨį
    0.10
    纹
    0.09
    ä¸ĢæľŁ
    0.09
    ä¹ĭéģĵ
    0.09
    обÑħодим
    0.09
    nder
    0.09
    otive
    0.09
     ÑģвÑıзи
    0.08
    åĬ¨éĿĻ
    0.08
    toa
    0.08
    Activations Density 0.002%

    No Known Activations