© 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. 60993
    Prev
    Next
    INDEX
    Explanations

    when context

    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
    asic
    -0.11
    æ±Ģ
    -0.09
    orthy
    -0.09
    å¾Ĺ以
    -0.09
    runner
    -0.08
    ä¹į
    -0.08
    éĥĵ
    -0.08
    ä½ľèĢħæľ¬äºº
    -0.08
    antic
    -0.08
    kür
    -0.08
    POSITIVE LOGITS
    æĺİ天
    0.17
    ä»ĬæĻļ
    0.15
    å°Ĩäºİ
    0.13
    å±ĬæŶ
    0.13
     tomorrow
    0.13
    æĺİæĹ¥
    0.12
    æľ¬åij¨
    0.11
     tonight
    0.11
    第äºĮ天
    0.11
    åĪ°æŶåĢĻ
    0.10
    Activations Density 0.127%

    No Known Activations