© 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. 33099
    Prev
    Next
    INDEX
    Explanations

    URLs starting with www

    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
    è¿Ļåľº
    -0.09
    ors
    -0.08
    个å°ı
    -0.08
    åĤį
    -0.08
    .googlecode
    -0.08
    å¸ĮæľĽèĥ½
    -0.08
    edList
    -0.08
    yü
    -0.08
    /ubuntu
    -0.08
    æ¼³
    -0.08
    POSITIVE LOGITS
    Glass
    0.10
    Ìģ
    0.09
    è´¯
    0.09
    à¹Ħà¸ĭ
    0.08
    æľ¬ç«Ļ
    0.08
    (crate
    0.08
    cale
    0.08
    çļĦæĥħ
    0.08
    kit
    0.08
    æ³¥åľŁ
    0.08
    Activations Density 0.197%

    No Known Activations