© 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. 20000
    Prev
    Next
    INDEX
    Explanations

    Kenya

    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
    é»Ķ
    -0.09
    伪
    -0.09
     Duis
    -0.09
    笪
    -0.09
    izr
    -0.09
    æ¬²æľĽ
    -0.08
     Durant
    -0.08
    åĬŀçIJĨ
    -0.08
    gatsby
    -0.08
    ä¸ĬåįĬå¹´
    -0.08
    POSITIVE LOGITS
     Kenya
    0.11
     Nairobi
    0.11
     ken
    0.10
     Lamb
    0.10
    çī¦
    0.10
    Ken
    0.10
    éĽĴ
    0.09
    é«ģ
    0.09
    åIJĥä»Ģä¹Ī
    0.09
    èĪŀ
    0.09
    Activations Density 0.077%

    No Known Activations