© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1382
    Prev
    Next
    INDEX
    Explanations

    Spanish cities and Spain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    åĬłæĭ¿å¤§
    -0.37
    åį°å°¼
    -0.36
     Winnipeg
    -0.33
     Haiti
    -0.32
    Canadian
    -0.32
    åĬłæĭ¿
    -0.31
    æ¹¾åĮº
    -0.31
     Hait
    -0.30
     Canadian
    -0.30
     Papua
    -0.30
    POSITIVE LOGITS
     Spain
    0.55
     Madrid
    0.47
    Spain
    0.46
     Spanish
    0.44
    西çıŃçīĻ
    0.43
     España
    0.39
    Spanish
    0.38
     Catalonia
    0.36
     Portugal
    0.35
     Barcelona
    0.35
    Activations Density 0.164%

    No Known Activations