© 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. 52553
    Prev
    Next
    INDEX
    Explanations

    organizations and standards

    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
    请éĢīæĭ©
    -0.09
    æĽ´é«ĺçļĦ
    -0.09
    меÑīа
    -0.09
    å®īç½®
    -0.09
    леÑĤ
    -0.09
    æĬ¥è¡¨
    -0.08
    èĽĽ
    -0.08
    _pg
    -0.08
    æħ¨
    -0.08
    好åĿı
    -0.08
    POSITIVE LOGITS
     drafting
    0.11
     dra
    0.10
    审议
    0.10
    修订
    0.09
     harmon
    0.09
    -chair
    0.09
    æĿĥå¨ģ
    0.09
    èµ·èįī
    0.09
     draft
    0.09
    ä¸ĸçķĮ第ä¸Ģ
    0.09
    Activations Density 0.129%

    No Known Activations