© 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. 53728
    Prev
    Next
    INDEX
    Explanations

    see what others do

    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
    çļĦä¸Ģéĥ¨åĪĨ
    -0.10
    ating
    -0.09
    çļĦäºĭ
    -0.09
    çıŃ车
    -0.09
    Advertis
    -0.08
    ç»ļ丽
    -0.08
    马æĭī
    -0.08
    åĨįéĢł
    -0.08
    æľīä¸Ģå®ļçļĦ
    -0.08
    æĤ²åĵĢ
    -0.08
    POSITIVE LOGITS
    æĹĥ
    0.10
    ropp
    0.09
    ä»Ģä¹Īåı«
    0.09
    æĪijçľĭ
    0.09
    roz
    0.09
    ÑĤели
    0.09
    evin
    0.09
    è¿Ļä¹Īå¤ļå¹´
    0.08
    entai
    0.08
    enia
    0.08
    Activations Density 0.004%

    No Known Activations