© 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. 12017
    Prev
    Next
    INDEX
    Explanations

    for German words

    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
    çŁ¥åIJį
    -0.10
    ä¹Łå¥½
    -0.09
     anders
    -0.09
    éĺµéĺµ
    -0.09
    çĸij
    -0.09
    临港
    -0.09
    ials
    -0.09
    为ä¹ĭ
    -0.09
    ilities
    -0.08
    æĶ¶å½ķ
    -0.08
    POSITIVE LOGITS
    ACK
    0.09
    æ¯ħåĬĽ
    0.09
    ç»°
    0.08
    سÙĪد
    0.08
    æĿ¥è¯´
    0.08
    楮
    0.08
    å³Ļ
    0.08
    æį¢åıĸ
    0.08
    é«¡
    0.08
    æĿ¯
    0.08
    Activations Density 0.147%

    No Known Activations