© 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. 56457
    Prev
    Next
    INDEX
    Explanations

    hoping for

    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
    abal
    -0.09
    <![
    -0.09
    æİ¥è¿ĩ
    -0.09
    æĺī
    -0.09
    ifter
    -0.09
    orst
    -0.09
    .Features
    -0.08
     Conte
    -0.08
    ression
    -0.08
    .rs
    -0.08
    POSITIVE LOGITS
    ä¸Ģ个好çļĦ
    0.10
    好çļĦ
    0.09
    åĸĤ
    0.09
    赢家
    0.08
    çļĦç¡®æĺ¯
    0.08
    æŀŀ
    0.08
    æĿŀ
    0.08
    é«ĺçļĦ
    0.08
    æĿ¥çĶµ
    0.08
     ÑħоÑĢо
    0.08
    Activations Density 0.007%

    No Known Activations