© 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. 8690
    Prev
    Next
    INDEX
    Explanations

    exact amount or monetary value

    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¸Ģéģĵ
    -0.10
    azu
    -0.09
    åĽ´çĿĢ
    -0.09
    ÙĨاÙĤ
    -0.09
    ç
    -0.09
    edList
    -0.08
     krist
    -0.08
    _THIS
    -0.08
    .Doc
    -0.08
    ä¿Ŀåį«
    -0.08
    POSITIVE LOGITS
    aug
    0.11
    ä»İå°ı
    0.10
    è¹²
    0.10
    éĴ±
    0.10
    bars
    0.09
    éĻĽ
    0.09
    纸
    0.09
     mint
    0.09
    ç½IJ
    0.09
     compliments
    0.08
    Activations Density 0.055%

    No Known Activations