© 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. 36940
    Prev
    Next
    INDEX
    Explanations

    in respect to

    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
    ergus
    -0.09
    æ¤Ĵ
    -0.09
    ç½ij讯
    -0.08
    æĬ¼
    -0.08
    3
    -0.08
    9
    -0.08
    头æĿ¡
    -0.08
    .rt
    -0.08
    å°Ŀ
    -0.08
    å°Ĩ士
    -0.08
    POSITIVE LOGITS
    debian
    0.10
    nox
    0.09
    -exclusive
    0.09
    ä¹Ŀå·ŀ
    0.09
    åĵ
    0.09
    ×Ļף
    0.09
    èĮī
    0.08
    ctor
    0.08
    æĪ´
    0.08
    åıijçĥŃ
    0.08
    Activations Density 0.003%

    No Known Activations