© 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. 21256
    Prev
    Next
    INDEX
    Explanations

    currency exchange rates

    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
    忽
    -0.10
    íĴĢ
    -0.09
    å¿Ļ
    -0.09
    план
    -0.09
    <!--[
    -0.08
    æłĬ
    -0.08
    åIJĿ
    -0.08
    å¾Ĵ
    -0.08
     <!--[
    -0.08
     biç
    -0.08
    POSITIVE LOGITS
    ç¦
    0.10
    çŁŃæľŁ
    0.09
    çĽħ
    0.09
    åħij
    0.09
    олÑı
    0.08
    çŁŃ线
    0.08
    寮
    0.08
    æĹħ游
    0.08
    åī¯ä½ľçĶ¨
    0.08
    Tour
    0.08
    Activations Density 0.034%

    No Known Activations