© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9025
    Prev
    Next
    INDEX
    Explanations

    modest size or scale

    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
    oment
    -0.09
    åħ³éĶ®æĺ¯
    -0.09
    wow
    -0.09
    ìį¨
    -0.09
    æľīæĽ´å¥½çļĦ
    -0.08
    æľĹ
    -0.08
    ÑĩаÑĤ
    -0.08
    è³ĵ
    -0.08
    valuate
    -0.08
    ç³Ł
    -0.08
    POSITIVE LOGITS
    ly
    0.13
    ions
    0.11
    -sized
    0.10
    åįĩ温
    0.10
    owo
    0.10
    åĪĨå·¥
    0.10
    ily
    0.10
     amounts
    0.09
    麽
    0.09
     xuyên
    0.09
    Activations Density 0.003%

    No Known Activations