© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 54698
    Prev
    Next
    INDEX
    Explanations

    events and actions completed

    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
    ä¹ŁæĽ¾
    -0.12
    ä¸Ģ度
    -0.12
    æĽ¾
    -0.11
    æĽ¾åľ¨
    -0.11
     eventually
    -0.10
    annels
    -0.09
    ä»ĸæĽ¾
    -0.09
    æĽ¾ç¶ĵ
    -0.09
    æĽ¾ç»ı
    -0.09
    ä»İæѤ
    -0.09
    POSITIVE LOGITS
    åı¦ä¸Ģ
    0.12
    åı¦å¤ĸä¸Ģ个
    0.09
    åı¦å¤ĸ
    0.09
    ragon
    0.09
    åĪĿæŃ¥
    0.08
     another
    0.08
    à¸ļรร
    0.08
    åı¦ä¸Ģä½į
    0.08
    /moment
    0.08
    æľĽ
    0.08
    Activations Density 0.176%

    No Known Activations