© 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. 8717
    Prev
    Next
    INDEX
    Explanations

    name born dates

    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
    mates
    -0.11
    ETO
    -0.10
    çľĭæĿ¥
    -0.10
    igans
    -0.10
    å¾Ģå¾Ģæĺ¯
    -0.09
     полов
    -0.09
    _te
    -0.09
    isers
    -0.09
    çľĭèµ·æĿ¥
    -0.09
    éļĶéŁ³
    -0.08
    POSITIVE LOGITS
    为代表çļĦ
    0.09
    ä¸Ģä¸ĸ
    0.09
    ski
    0.08
    rog
    0.08
    å°ıæŶ
    0.08
    ï½¢
    0.08
    åĩºå¸Ńä¼ļè®®
    0.08
    ðŁı»
    0.08
    oe
    0.08
    sert
    0.08
    Activations Density 0.273%

    No Known Activations