© 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. 11142
    Prev
    Next
    INDEX
    Explanations

    future imports

    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
    cheid
    -0.09
    ä¿¡èµĸ
    -0.09
    ç½ijéĢļ
    -0.09
    uez
    -0.08
    å¾Ī满æĦı
    -0.08
    æķĻè®Ń
    -0.08
    ä½Ĩä¸įéĻIJäºİ
    -0.08
    æŃ»è§Ĵ
    -0.08
    çī¹åĪ«æĺ¯
    -0.08
    du
    -0.08
    POSITIVE LOGITS
    å°ĨæĿ¥
    0.14
    æľªæĿ¥çļĦ
    0.11
    æľªæĿ¥
    0.10
    .future
    0.10
    Slim
    0.10
    baum
    0.10
    .Future
    0.10
     ÑĢазвиÑĤие
    0.09
    future
    0.09
     fut
    0.09
    Activations Density 0.021%

    No Known Activations