© 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. 7742
    Prev
    Next
    INDEX
    Explanations

    or introducing alternatives

    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¸īç§į
    -0.10
    æĬ¤
    -0.10
    edor
    -0.10
    åħļæĶ¿
    -0.10
     Intern
    -0.09
    _critical
    -0.09
    å¾Īæ¸ħæ¥ļ
    -0.09
    æľªç»ıæİĪæĿĥ
    -0.09
    æķ°æį®ä¸Ńå¿ĥ
    -0.09
    é¥Ń
    -0.09
    POSITIVE LOGITS
    handler
    0.09
    ÑĢÑĥÑģ
    0.09
     Ea
    0.08
    ç²¾åįİ
    0.08
     allegedly
    0.08
    æĢĢæĬ±
    0.08
    ibus
    0.08
     handler
    0.08
    为ä¹ĭ
    0.08
    åĪĿ次
    0.07
    Activations Density 0.078%

    No Known Activations