© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20690
    Prev
    Next
    INDEX
    Explanations

    beach locations

    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
    å¤©åºľ
    -0.09
    itarian
    -0.09
     бÑĭ
    -0.09
    vince
    -0.09
    æŶè£ħ
    -0.09
    arus
    -0.08
    太ä¹ħ
    -0.08
     lá»ĩ
    -0.08
    ar
    -0.08
    æĸ¯é¡¿
    -0.08
    POSITIVE LOGITS
    ably
    0.09
    вод
    0.09
    eron
    0.09
    intl
    0.09
    uml
    0.08
    elder
    0.08
    fulness
    0.08
    æĥħ趣
    0.08
    ério
    0.08
    éĹ´çļĦ
    0.08
    Activations Density 0.003%

    No Known Activations