© 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. 8705
    Prev
    Next
    INDEX
    Explanations

    banquet, gala, dinner, function

    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
       
    -0.10
    è¢Ĥ
    -0.10
    unter
    -0.09
    sut
    -0.09
    ERIC
    -0.08
    ORT
    -0.08
    ya
    -0.08
    å©¢
    -0.08
    idget
    -0.08
    dition
    -0.08
    POSITIVE LOGITS
    itos
    0.10
    zug
    0.09
     halls
    0.09
    دÙĬÙĨ
    0.09
    eer
    0.09
    astle
    0.08
    AndGet
    0.08
    大å¦Ī
    0.08
    æ¶Īè´¹åĵģ
    0.08
    ç³Ł
    0.08
    Activations Density 0.002%

    No Known Activations