© 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. 36951
    Prev
    Next
    INDEX
    Explanations

    mutual agreement or benefit

    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
    åĨ¤
    -0.11
    ãģµ
    -0.09
    mail
    -0.09
    æŃ·
    -0.08
    并ä¸İ
    -0.08
    æŶèĬĤ
    -0.08
    åĵĹ
    -0.08
    دا
    -0.08
    ä»ĬæĻļ
    -0.08
    ä½ĵåĪ¶
    -0.08
    POSITIVE LOGITS
    äºĴåĪ©
    0.12
    (mut
    0.10
    èĢģ人家
    0.10
     mutually
    0.09
    äºĴ
    0.09
    reamble
    0.09
    å¢ŀéķ¿
    0.09
    (rec
    0.09
    emble
    0.08
    ware
    0.08
    Activations Density 0.023%

    No Known Activations