© 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. 55578
    Prev
    Next
    INDEX
    Explanations

    German umlauts and special characters

    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
    ien
    -0.10
     же
    -0.08
    ane
    -0.08
     ÑĢеÑĪи
    -0.08
    æĿ¥è¯´
    -0.08
    _IMM
    -0.08
    ί
    -0.08
    ä¾Ĩ說
    -0.08
    该éĻ¢
    -0.08
    zy
    -0.08
    POSITIVE LOGITS
    æ¼Ĥæµģ
    0.10
    è¿Ļ对äºİ
    0.10
    æºIJæºIJ
    0.10
    UCE
    0.09
    æ¯ĶæĪij
    0.09
    ä»Ģä¹Īåij¢
    0.09
    ลา
    0.09
    çĥ¦èºģ
    0.09
    好åIJĹ
    0.09
    以便
    0.09
    Activations Density 0.063%

    No Known Activations