© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38395
    Prev
    Next
    INDEX
    Explanations

    UK, Britain, London, England

    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
    深交æīĢ
    -0.10
     Alaska
    -0.09
    vang
    -0.09
    inas
    -0.09
     Santa
    -0.09
    çĻ½å®«
    -0.09
    Santa
    -0.09
    ä¸Ģä¸ĭåŃIJ
    -0.09
    çŃIJ
    -0.09
     Puerto
    -0.08
    POSITIVE LOGITS
    èĭ±åĽ½
    0.25
    èĭ±æł¼åħ°
    0.22
    èĭ±éķij
    0.21
     England
    0.20
    伦æķ¦
    0.20
    èĭ±åľĭ
    0.20
     Britain
    0.20
    British
    0.20
     British
    0.20
    Britain
    0.19
    Activations Density 0.711%

    No Known Activations