© 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. 32594
    Prev
    Next
    INDEX
    Explanations

    dishes and meals

    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
    åį¯
    -0.10
    rapper
    -0.09
    宽æĿ¾
    -0.09
    æ¥ł
    -0.09
    车éĺŁ
    -0.09
     Sterling
    -0.08
    çīĮåŃIJ
    -0.08
    åĨħè¡£
    -0.08
    èµŃ
    -0.08
    楷
    -0.08
    POSITIVE LOGITS
    ä¸Ģéģĵ
    0.11
     dishes
    0.10
    çħ²
    0.10
    ä¸Ģ项
    0.10
    èĤĺ
    0.10
    æ¡Įä¸Ĭ
    0.10
    大åħ¨
    0.09
     dish
    0.09
     Cald
    0.09
     Dish
    0.09
    Activations Density 0.081%

    No Known Activations