© 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. 56812
    Prev
    Next
    INDEX
    Explanations

    food processes and measurements

    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
    wing
    -0.09
    çĽĬ
    -0.09
    æĮ½åĽŀ
    -0.09
    efore
    -0.09
    é¢Ŀ
    -0.08
    unded
    -0.08
    YM
    -0.08
    å¢ŀæ·»
    -0.08
    æ©Ħæ¦Ħ
    -0.08
    ledged
    -0.08
    POSITIVE LOGITS
    浸泡
    0.10
    çłĶ
    0.09
    iken
    0.09
    漫
    0.09
    æĽĿ
    0.09
    ahn
    0.09
    ren
    0.09
    åĢĻ
    0.09
    æļ´
    0.08
     Master
    0.08
    Activations Density 0.065%

    No Known Activations