© 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. 18096
    Prev
    Next
    INDEX
    Explanations

    future plans or goals

    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
    æĪij说
    -0.09
    ä»Ģä¹Īéĥ½ä¸į
    -0.09
    éĹ®
    -0.08
    åķı
    -0.08
    åħĦ
    -0.08
    主ä¸ļ
    -0.08
    注æĦıåĪ°
    -0.08
    zyst
    -0.08
    åįĹåĮĹ
    -0.08
    èľ¥
    -0.08
    POSITIVE LOGITS
     future
    0.10
    èĩªå·±çļĦ
    0.09
    åIJįçīĩ
    0.08
     growth
    0.08
    æķ£åıijçĿĢ
    0.08
    uses
    0.08
    æľªæĿ¥çļĦ
    0.08
    åĿĮ
    0.08
    æľĽåİ»
    0.08
    rega
    0.08
    Activations Density 0.029%

    No Known Activations