© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51543
    Prev
    Next
    INDEX
    Explanations

    your inbox

    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
    ä¸Ģç»ı
    -0.09
    讼
    -0.09
    æį¡
    -0.09
    amics
    -0.09
    egen
    -0.08
    天åłĤ
    -0.08
    å®ŀçī©
    -0.08
    èĵ¦
    -0.08
    天èĬ±æĿ¿
    -0.08
    åĶ¤éĨĴ
    -0.08
    POSITIVE LOGITS
    èħķ
    0.12
    è£Ļ
    0.08
     Sass
    0.08
    æī§æķĻ
    0.08
    åľ»
    0.08
    Ò§
    0.08
    arb
    0.08
    åį±
    0.08
    æ»ŀ
    0.08
    ä¸į平衡
    0.08
    Activations Density 0.009%

    No Known Activations