© 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. 34333
    Prev
    Next
    INDEX
    Explanations

    found stray or discovered

    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
    éĺħè§Ī
    -0.09
    é¢Ģ
    -0.09
    athed
    -0.08
    廪
    -0.08
    æµĵåİļ
    -0.08
    ignon
    -0.08
    åİļéĩį
    -0.08
    çĪ±å¥½
    -0.08
    æݩ饰
    -0.08
    RLF
    -0.08
    POSITIVE LOGITS
    æĹłäºº
    0.12
    æį¡
    0.11
    没人
    0.10
    æµģ浪
    0.10
    æķijåĬ©
    0.10
    被人
    0.10
    åĵªåĦ¿
    0.09
    å²Ĺ
    0.09
    交ç»Ļ
    0.09
     lẫn
    0.09
    Activations Density 0.057%

    No Known Activations