© 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. 38475
    Prev
    Next
    INDEX
    Explanations

    educational contexts

    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¸ĢåĽŀäºĭ
    -0.10
    åIJĽåŃIJ
    -0.09
    æµĨ
    -0.09
    éĵ²
    -0.09
    妥åĸĦ
    -0.09
    pute
    -0.09
    reib
    -0.09
    alah
    -0.09
    å·¢
    -0.08
    .Broadcast
    -0.08
    POSITIVE LOGITS
    辫
    0.10
    zos
    0.09
    çijĻ
    0.09
    è¿ĽæŃ¥
    0.09
    éĢļ讯
    0.09
    ãģ½
    0.09
    åŃº
    0.08
    æĸĩåĮĸèīºæľ¯
    0.08
     ops
    0.08
     ras
    0.08
    Activations Density 0.019%

    No Known Activations