© 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. 22380
    Prev
    Next
    INDEX
    Explanations

    can help

    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
    inish
    -0.09
    Reuse
    -0.09
    æĹłå¿§
    -0.09
    ä¸įæĪIJ
    -0.09
    æĺ¯åı¯ä»¥
    -0.09
    æĢł
    -0.09
    ç¼Ĵ
    -0.08
    è¯ķçĿĢ
    -0.08
    人æ°ijéĵ¶è¡Į
    -0.08
    ä¸ĬäºĨ
    -0.08
    POSITIVE LOGITS
    íķ´ì£¼
    0.12
    帮
    0.11
    å¸®ä½ł
    0.10
    帮åĬ©
    0.10
    帮å¿Ļ
    0.10
    åįıåĬ©
    0.10
    åįĶåĬ©
    0.09
     help
    0.09
    èĥľä»»
    0.09
    幫
    0.09
    Activations Density 0.029%

    No Known Activations