© 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. 63685
    Prev
    Next
    INDEX
    Explanations

    place names ending in "a"

    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
    æŶéĹ´èĬĤçĤ¹
    -0.10
    éħĭ
    -0.10
    ä¸Ģ对ä¸Ģ
    -0.09
    åĪ¤
    -0.09
    æł¹åŁº
    -0.09
    æłĢ
    -0.09
    ä¹ĭåŁİ
    -0.09
    æīĵåĵį
    -0.09
    ató
    -0.08
    æ·ij
    -0.08
    POSITIVE LOGITS
    /commons
    0.11
    æĮĩåįĹ
    0.10
    allah
    0.09
    é¹ħ
    0.08
    LT
    0.08
    à¸Ĥา
    0.08
    人æ°ij
    0.08
    ä¸ļä½Ļ
    0.08
    åijĨ
    0.08
    ä»ij
    0.08
    Activations Density 0.227%

    No Known Activations