© 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. 4383
    Prev
    Next
    INDEX
    Explanations

    copyright information

    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
    å©ļ
    -0.10
    绣绣
    -0.09
    åı¯çĪ±
    -0.08
    ä¿Ŀå¯Ĩ
    -0.08
    认
    -0.08
    æĭŁ
    -0.08
     fatt
    -0.08
    .annot
    -0.08
    æĿ¥çľĭçľĭ
    -0.08
    olec
    -0.08
    POSITIVE LOGITS
    본
    0.08
    ewood
    0.08
    Lite
    0.08
    ä¸įèĩ³äºİ
    0.08
    åģ¶
    0.08
    Ñģка
    0.08
    ï¹
    0.08
    æīĢæıIJä¾ĽçļĦ
    0.08
    ä¸į容æĺĵ
    0.08
    çŁ¾
    0.08
    Activations Density 0.048%

    No Known Activations