© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21608
    Prev
    Next
    INDEX
    Explanations

    pen or Parker

    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
    æ¼Ķä¹ł
    -0.09
    å²ģ以ä¸ĭ
    -0.09
    vim
    -0.09
    ower
    -0.09
    沿
    -0.08
    åĭĺæİ¢
    -0.08
    lever
    -0.08
    纺
    -0.08
    oner
    -0.08
    æį¢
    -0.08
    POSITIVE LOGITS
    æĸĹå¿Ĺ
    0.10
    é¬ĵ
    0.09
    åĮ¹
    0.09
    椿
    0.08
    gress
    0.08
    æ°ijæĹıæĸĩåĮĸ
    0.08
    æĹı
    0.08
    isy
    0.08
    é¢ł
    0.08
    家乡
    0.08
    Activations Density 0.004%

    No Known Activations