© 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. 56206
    Prev
    Next
    INDEX
    Explanations

    Belgian and Belgium

    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
    管å§Ķä¼ļ
    -0.10
    agua
    -0.10
    اء
    -0.10
    ØŃÙĪا
    -0.09
    涧
    -0.09
    ely
    -0.09
    /reset
    -0.09
    ello
    -0.08
    æµĻæ±Łçľģ
    -0.08
    ä¸Ńä¿Ħ
    -0.08
    POSITIVE LOGITS
     Belg
    0.10
     Belgi
    0.10
    toast
    0.09
    ìĤ¬íķŃ
    0.09
    ignum
    0.09
    èĬ
    0.09
    -American
    0.08
    工夫
    0.08
    antine
    0.08
    佬
    0.08
    Activations Density 0.007%

    No Known Activations