© 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. 11043
    Prev
    Next
    INDEX
    Explanations

    state or condition

    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
    ORN
    -0.09
    zag
    -0.08
    nga
    -0.08
    ä¸ĢæµģçļĦ
    -0.08
    oby
    -0.08
     shark
    -0.08
     Shark
    -0.07
    å·²ç»ıè¶ħè¿ĩ
    -0.07
    ed
    -0.07
    OA
    -0.07
    POSITIVE LOGITS
    å¼ĢåѦ
    0.12
    iek
    0.11
    æħ£
    0.10
    常æĢģåĮĸ
    0.10
    èµĽåIJİ
    0.10
    æѤ类
    0.09
    æı®
    0.09
    æѤæĸĩ
    0.09
     влад
    0.09
    æİı
    0.09
    Activations Density 0.341%

    No Known Activations