© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20216
    Prev
    Next
    INDEX
    Explanations

    to the

    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
    .cur
    -0.09
    æľķ
    -0.09
    èī²ç´ł
    -0.09
    åĽĽçº§
    -0.09
    çķĻä½ı
    -0.08
    æ¾
    -0.08
    Aggregate
    -0.08
    è¿«
    -0.08
     cur
    -0.08
    强迫
    -0.08
    POSITIVE LOGITS
    æķĮ人
    0.14
    对æīĭ
    0.12
    ç«ŀäºī对æīĭ
    0.10
    对æĸ¹
    0.10
    è°Ĺ
    0.09
    æ°ĵ
    0.09
    ç»ĻäºĨ
    0.09
    ãģ¾ãĤĮ
    0.09
    è´¼
    0.09
    æķµ
    0.09
    Activations Density 0.071%

    No Known Activations