© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7609
    Prev
    Next
    INDEX
    Explanations

    points per game

    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
    åĴİ
    -0.09
    壤
    -0.09
    åŁ
    -0.08
    ç»ĻæĤ¨
    -0.08
    æĬķèµĦåŁºéĩij
    -0.08
    ä¸ĩ亿
    -0.08
    æĸ°æĶ¿
    -0.08
    ä¿Ŀå®Ī
    -0.08
    éĻIJè´Ń
    -0.08
    æī¿åıĹ
    -0.08
    POSITIVE LOGITS
    ç³»åĪĹæ´»åĬ¨
    0.08
    OfString
    0.08
    è¹ij
    0.08
    æİ¥
    0.08
     transports
    0.08
    ç«Ļç«ĭ
    0.08
     Petite
    0.08
    麻éĨī
    0.08
     FOX
    0.07
    nyder
    0.07
    Activations Density 0.009%

    No Known Activations