© 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. 32950
    Prev
    Next
    INDEX
    Explanations

    credit card or debit card

    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
    说è¿ĩ
    -0.10
    æĥ³è¿ĩ
    -0.09
    ULE
    -0.09
    PEC
    -0.08
    inee
    -0.08
    éĺIJæĺİ
    -0.08
    èģĶ绾
    -0.08
    ç¼
    -0.08
    æĿĥçĽĬ
    -0.08
     Shay
    -0.08
    POSITIVE LOGITS
    -based
    0.09
    äºĨåĩºæĿ¥
    0.09
    -Based
    0.09
    çļĦ帮åĬ©ä¸ĭ
    0.09
    çī¹éķ¿
    0.09
    åħħå½ĵ
    0.09
    æ¯ıèĤ¡
    0.09
    æīĢæıIJä¾ĽçļĦ
    0.09
    çļĦä¸Ģéĥ¨åĪĨ
    0.08
    nosis
    0.08
    Activations Density 0.749%

    No Known Activations