© 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. 55517
    Prev
    Next
    INDEX
    Explanations

    London place names

    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
     saÄŁlam
    -0.08
    é©»
    -0.08
    PUR
    -0.08
    åħĭæĭī
    -0.08
    MRI
    -0.08
    夷
    -0.08
    è¿ŀäºij港
    -0.08
    æ²ħ
    -0.08
    ujÄħc
    -0.07
    овиÑĩ
    -0.07
    POSITIVE LOGITS
    伦æķ¦
    0.13
    æµ·æ·Ģ
    0.13
    åľ¨åĮĹ京
    0.13
    æµ·æ·ĢåĮº
    0.12
     London
    0.12
    London
    0.10
     london
    0.10
    æĪIJé¾Ļ
    0.10
    åĮĹ京å¸Ĥ
    0.09
     borough
    0.09
    Activations Density 0.061%

    No Known Activations