© 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. 55628
    Prev
    Next
    INDEX
    Explanations

    un + word

    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
    ä¸İä¼Ĺä¸įåIJĮ
    -0.09
    أخبار
    -0.09
    é¢ĺæĿIJ
    -0.09
    ssue
    -0.09
    urch
    -0.09
    lesia
    -0.09
    ÅĦ
    -0.08
    .MODE
    -0.08
    onne
    -0.08
     Liberals
    -0.08
    POSITIVE LOGITS
    禽
    0.10
    enting
    0.10
    ness
    0.09
    éģ½
    0.09
    çĦ¶æĺ¯
    0.09
    otify
    0.09
    /un
    0.09
    aar
    0.09
    èĢĮåıĪ
    0.09
    äºĨå¤ļå°ij
    0.08
    Activations Density 0.028%

    No Known Activations