© 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. 50273
    Prev
    Next
    INDEX
    Explanations

    trucks, vehicles, and trailers

    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
    é³ĥ
    -0.09
    è¢ľ
    -0.09
     gated
    -0.09
    æĦŁ
    -0.09
    é¢Ħ订
    -0.09
    ä¸Ĭ游
    -0.09
     bracelet
    -0.08
    讥
    -0.08
    ç²¥
    -0.08
     gover
    -0.08
    POSITIVE LOGITS
    车ä¸Ĭ
    0.11
    ä¹ĺ客
    0.11
    车åİ¢
    0.10
    æĸ°åĬł
    0.10
    车åĨħ
    0.10
    å¹³åı°
    0.09
     passengers
    0.09
     Platform
    0.09
    è¿ĽåŁİ
    0.09
    å¹³åı°ä¸Ĭ
    0.09
    Activations Density 0.120%

    No Known Activations