© 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. 9119
    Prev
    Next
    INDEX
    Explanations

    currency and numbers

    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
    åįģå¤ļ
    -0.09
    åĽĽäºĶ
    -0.08
    è·³åĩº
    -0.07
    åįģä½Ļ
    -0.07
     somehow
    -0.07
    ä¸ĩä½Ļ
    -0.07
    æĪIJ绩
    -0.07
    çĤ¹éĴŁ
    -0.07
    ignored
    -0.07
    ENA
    -0.07
    POSITIVE LOGITS
    æł·çļĦ
    0.11
    ç¦ħ
    0.10
    ä¸įåıĺ
    0.10
    æľĢä½İ
    0.10
    ä¸Ģå¾ĭ
    0.10
    æłĩåĩĨ
    0.10
    çļĦæłĩåĩĨ
    0.09
    çİ°è¡Į
    0.09
    åºķ线
    0.09
    éĢļ常
    0.09
    Activations Density 0.074%

    No Known Activations