© 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. 48846
    Prev
    Next
    INDEX
    Explanations

    html table link tracking

    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
    è¾
    -0.10
    iev
    -0.09
    åĽĽæĸ¹
    -0.08
    ç¬ij
    -0.08
    转
    -0.08
    æĢ¥äºİ
    -0.08
     cavern
    -0.08
    æ´ŀ
    -0.08
     alert
    -0.07
     Futures
    -0.07
    POSITIVE LOGITS
    æĶ¾åģĩ
    0.10
    åIJĪæ³ķæĢ§
    0.10
    ForRow
    0.10
    æĴ©
    0.09
     nhắc
    0.09
    missible
    0.09
    atro
    0.09
     hạ
    0.09
    åħ³åģľ
    0.09
    æłĩæĺİ
    0.09
    Activations Density 0.100%

    No Known Activations