© 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. 2836
    Prev
    Next
    INDEX
    Explanations

    time before an event

    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
    ä¹ĭéģĵ
    -0.10
    Ñģкоп
    -0.09
    EMS
    -0.08
     follower
    -0.08
     ÙĪاÙĦت
    -0.08
    .cum
    -0.08
     пÑĢиÑĩ
    -0.08
    ÑĢиÑģ
    -0.08
    arily
    -0.08
    <![
    -0.08
    POSITIVE LOGITS
     Bast
    0.09
    建åĨĽ
    0.09
    èIJ¥
    0.09
    ches
    0.08
    温馨
    0.08
    å®ŀéĻħæĥħåĨµ
    0.08
    /pp
    0.08
     mature
    0.08
    æĽĻåħī
    0.08
    æľ¬æľŁ
    0.08
    Activations Density 0.013%

    No Known Activations