© 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. 21144
    Prev
    Next
    INDEX
    Explanations

    not alone, only one, first

    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
    mai
    -0.10
    åIJĦæł·
    -0.08
    èĢĮä¸įæĺ¯
    -0.08
     heed
    -0.08
    æĹłæīĢ
    -0.08
    ä¸Ģå¦Ĥ
    -0.08
    åIJĪä¸Ģ
    -0.08
    ä¸įåĩº
    -0.08
    uard
    -0.08
    tron
    -0.08
    POSITIVE LOGITS
    atform
    0.09
    ursal
    0.09
    æľīå¾Īå¤ļ
    0.09
     Äijá»Ŀi
    0.08
    ç²ī
    0.08
    ivi
    0.08
    åѤ
    0.08
    åħ¶æ¬¡æĺ¯
    0.08
    isk
    0.08
    ä¿Ħ
    0.08
    Activations Density 0.007%

    No Known Activations