© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8362
    Prev
    Next
    INDEX
    Explanations

    search activity

    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
    /from
    -0.11
    cert
    -0.09
    鬲
    -0.09
    urf
    -0.09
    æĥľ
    -0.09
    åĢ¼å¾Ĺä¸Ģ
    -0.09
    äºĨä¸ĢäºĽ
    -0.08
    -profit
    -0.08
    è¾į
    -0.08
    妫
    -0.08
    POSITIVE LOGITS
    èĦijæµ·
    0.10
    ä¾Ľç»Ļ侧
    0.10
    IZER
    0.10
    quine
    0.09
    åĽĽåij¨
    0.09
     облаÑģÑĤи
    0.09
    SHIP
    0.09
     Ø£ÙĨØŃاء
    0.09
    ritte
    0.09
    ä¸ºæł¸å¿ĥçļĦ
    0.09
    Activations Density 0.026%

    No Known Activations