© 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. 3518
    Prev
    Next
    INDEX
    Explanations

    German marriage certificate translation

    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
     mu
    -0.10
     мÑĥ
    -0.10
     MU
    -0.10
    (mu
    -0.09
    éľĵ
    -0.09
    _emit
    -0.09
    ç¼Ģ
    -0.09
    ays
    -0.09
    .mu
    -0.09
    ember
    -0.08
    POSITIVE LOGITS
    代åĬŀ
    0.11
    çĦ±
    0.10
    æ³½
    0.09
    解åĨ³æĸ¹æ¡Ī
    0.09
    é«ĺéĢŁå¢ŀéķ¿
    0.09
    让æĤ¨
    0.09
    涯
    0.09
    åĴ¨è¯¢
    0.08
    é«ĺåĵģè´¨
    0.08
    åģļ人
    0.08
    Activations Density 0.340%

    No Known Activations