© 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. 62542
    Prev
    Next
    INDEX
    Explanations

    book titles and author names

    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
    èĬĤ缮ä¸Ń
    -0.10
    è¾Ł
    -0.10
    éĽĨä½ĵ
    -0.09
    æ·Ļ
    -0.09
    身形
    -0.09
    çģ«èĬ±
    -0.09
    çŁ
    -0.09
    觥
    -0.09
    å¹»
    -0.09
    å²ij
    -0.08
    POSITIVE LOGITS
    讼
    0.09
    ä¹łæĥ¯äºĨ
    0.08
    åľ¨æĹ¥æľ¬
    0.08
    illance
    0.08
    Alg
    0.08
    è¿ĻåĿĹ
    0.08
    NAL
    0.08
    unner
    0.08
    ulate
    0.08
    èł¢
    0.08
    Activations Density 0.052%

    No Known Activations