© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 9468
    Prev
    Next
    INDEX
    Explanations

    on part of

    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
    èĪį
    -0.10
    å¾ĺå¾Ĭ
    -0.09
    线索
    -0.09
    regon
    -0.09
    .Prop
    -0.09
    çģ°èī²
    -0.09
    ennen
    -0.09
    ä¸įäºĨ
    -0.09
    ippo
    -0.08
    erner
    -0.08
    POSITIVE LOGITS
     behalf
    0.15
    å°ıç¼ĸ
    0.10
    بÙĪØ±
    0.09
    ington
    0.09
    è¿Ļ对
    0.09
    èģĮæĿĥ
    0.09
    ç¬ĶèĢħ
    0.09
    æľ¬ä¹¦
    0.09
    urb
    0.08
    磫
    0.08
    Activations Density 0.040%

    No Known Activations