© 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. 5334
    Prev
    Next
    INDEX
    Explanations

    car duster

    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
    åIJij社ä¼ļ
    -0.10
    人æĢ§
    -0.09
    éĢı
    -0.09
    ç»Ĭ
    -0.09
     TNT
    -0.09
     sight
    -0.09
    æ°Ķæģ¯
    -0.09
    æĭ¦
    -0.09
    å¾ģ
    -0.08
    çĦ°
    -0.08
    POSITIVE LOGITS
    丢失
    0.10
    çĻ¾å¼º
    0.10
    åģľè½¦åľº
    0.09
    车主
    0.09
    åģľè½¦ä½į
    0.09
    çļ±çº¹
    0.09
    车ä½į
    0.09
     parking
    0.09
    UDA
    0.09
    èŁł
    0.09
    Activations Density 0.062%

    No Known Activations