© 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. 48880
    Prev
    Next
    INDEX
    Explanations

    warning message

    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
    bing
    -0.10
    rics
    -0.10
    INES
    -0.10
    çĦ¦
    -0.09
    麽
    -0.09
    ationally
    -0.09
    nts
    -0.09
    ULE
    -0.09
    ule
    -0.09
    illion
    -0.09
    POSITIVE LOGITS
    âļł
    0.10
    ìŀ¥ìĿĦ
    0.10
    æĢ§çļĦ
    0.10
    anca
    0.09
    ä»Ģä¹Īåij¢
    0.09
    èĢĢçľ¼
    0.09
    /alert
    0.09
    ncia
    0.08
    ingly
    0.08
    .TRAILING
    0.08
    Activations Density 0.031%

    No Known Activations